Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection | Paper Citation Record

Observation db3981e3-74ce-482e-bbb4-dd3ac75ca216 · outbound

This paper cites Bridg- ing the gap between object and image-level representations for open-vocabulary detection.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Bridg- ing the gap between object and image-level representations for open-vocabulary detection

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:33.897362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17fc7182-20d2-41c2-95e3-017c4828fb4d · outbound

This paper cites End- to-end object detection with transformers.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection End- to-end object detection with transformers

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:33.902105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b03136e5-d99e-44cd-bf34-03704abbffe5 · outbound

This paper cites Emerg- ing properties in self-supervised vision transformers.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Emerg- ing properties in self-supervised vision transformers

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:33.908058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b891a697-38a8-4291-87b8-3a0063cc9ca9 · outbound

This paper cites Generic attention- model explainability for interpreting bi-modal and encoder- decoder transformers.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Generic attention- model explainability for interpreting bi-modal and encoder- decoder transformers

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:33.913872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaa2407a-400c-4507-8cbb-083426c58af3 · outbound

This paper cites CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-12T19:14:34.741882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e5f1f7ba-2173-4c7a-a937-a29ce4570943 · outbound

This paper cites Efficient video action detection with token dropout and context refinement.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Efficient video action detection with token dropout and context refinement

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:33.926112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 751bcd4b-75e4-4952-9bb9-4b5230a32a7a · outbound

This paper cites Watch only once: An end-to-end video action detection framework.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Watch only once: An end-to-end video action detection framework

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:33.931019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e35feb40-0671-4a36-b17c-bee968bc33d5 · outbound

This paper cites Gabriellav2: Towards better generalization in surveillance videos for ac- tion detection.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Gabriellav2: Towards better generalization in surveillance videos for ac- tion detection

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:33.938524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 899f6d60-3d9a-423f-95ef-a1f52c97fe31 · outbound

This paper cites An image is worth 16x16 words: Trans- formers for image recognition at scale.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection An image is worth 16x16 words: Trans- formers for image recognition at scale

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:33.942737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98a2ede4-d1b3-4ed4-89fc-1cc8556ffbad · outbound

This paper cites Learning to prompt for open-vocabulary ob- ject detection with vision-language model.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Learning to prompt for open-vocabulary ob- ject detection with vision-language model

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:33.947581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbd0b121-fc8f-4d39-82ed-b4a83da6c90e · outbound

This paper cites Holistic interaction transformer network for action detection.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Holistic interaction transformer network for action detection

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:33.953166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbbb3167-c1e4-4cb3-9bdd-c19cd89a3440 · outbound

This paper cites X3d: Expanding architectures for efficient video recognition.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection X3d: Expanding architectures for efficient video recognition

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:33.958245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1d8fe21-be1c-4d83-bd36-40bd9b5e3e62 · outbound

This paper cites Slowfast networks for video recognition.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Slowfast networks for video recognition

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.305254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 39c3202b-f348-4ef9-9528-cdfa635e7663 · outbound

This paper cites Clip-adapter: Better vision-language models with feature adapters.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Clip-adapter: Better vision-language models with feature adapters

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.289572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6c8f9fde-1643-4644-a992-a20489ee6010 · outbound

This paper cites Adamixer: A fast-converging query-based object detector.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Adamixer: A fast-converging query-based object detector

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.275566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3647d439-e593-4e2e-9808-f6f413784297 · outbound

This paper cites Video action transformer network.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Video action transformer network

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.261882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ada785ec-8665-41e8-a8f3-868448bcf185 · outbound

This paper cites Ava: A video dataset of spatio-temporally localized atomic visual actions.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Ava: A video dataset of spatio-temporally localized atomic visual actions

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.245927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0948440f-5a6f-41f8-b49b-dbc1d9aef6cd · outbound

This paper cites Mask r-cnn.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Mask r-cnn

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.233579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8dcb99de-b9f4-4ade-afba-f62d7bb1d01e · outbound

This paper cites Mask r-cnn.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Mask r-cnn

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.219321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b7ff74fc-5739-40ef-81bb-4a05f78aa929 · outbound

This paper cites Interaction-aware prompting for zero-shot spatio-temporal action detection.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Interaction-aware prompting for zero-shot spatio-temporal action detection

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.204945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c0f167db-0d6f-4c01-b12b-11a15a5744f7 · outbound

This paper cites Towards understanding ac- tion recognition.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Towards understanding ac- tion recognition

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.191381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 48bfafee-2a01-41bd-a998-cac1e8fb3254 · outbound

This paper cites Prompting visual-language models for efficient video understanding.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Prompting visual-language models for efficient video understanding

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.174641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3f2e8739-d94a-49ee-8651-719104ac68a4 · outbound

This paper cites Prompting visual-language models for efficient video understanding.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Prompting visual-language models for efficient video understanding

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.162136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 58b2af96-fcf7-41c8-b199-885dd85a5e02 · outbound

This paper cites Action tubelet detector for spatio- temporal action localization.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Action tubelet detector for spatio- temporal action localization

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.147873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f4cf0649-040f-417d-80a7-279a2b3bd1cd · outbound

This paper cites Region- aware pretraining for open-vocabulary object detection with vision transformers.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Region- aware pretraining for open-vocabulary object detection with vision transformers

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.133135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 13de2aab-4ba6-495f-9b9c-b9dac35bac06 · outbound

This paper cites You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:34.042842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 627737ca-7693-4dc1-aec4-a29fc32d4c5d · outbound

This paper cites F-vlm: Open-vocabulary object detection upon frozen vision and language models.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection F-vlm: Open-vocabulary object detection upon frozen vision and language models

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.115041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a6de3308-f534-4333-adba-57ddb94b64a6 · outbound

This paper cites Multisports: A multi-person video dataset of spatio-temporally localized sports actions.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Multisports: A multi-person video dataset of spatio-temporally localized sports actions

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.099488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 992132a9-a5a3-44d3-a65c-db8ca27af360 · outbound

This paper cites Exploring plain vision transformer backbones for object de- tection.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Exploring plain vision transformer backbones for object de- tection

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.082400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d6060094-1d26-4859-9fa5-e6c7837ca89c · outbound

This paper cites A Closer Look at the Explainability of Contrastive Language-Image Pre-training.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection A Closer Look at the Explainability of Contrastive Language-Image Pre-training

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:34.072739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d5d97d2-4307-47ec-bd8c-6a10c6b79641 · outbound

This paper cites Exploring Visual Interpretability for Contrastive Language-Image Pre-training.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Exploring Visual Interpretability for Contrastive Language-Image Pre-training

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:34.090090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d102cf0-b0a6-4361-bb6a-81b2b6873817 · outbound

This paper cites Open-vocabulary semantic segmentation with mask-adapted clip.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Open-vocabulary semantic segmentation with mask-adapted clip

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.064805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 64abda54-12b0-469d-9f22-61e2b7c3dd2a · outbound

This paper cites Learning object-language alignments for open-vocabulary object de- tection.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Learning object-language alignments for open-vocabulary object de- tection

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.050592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 782e6c26-1364-4b98-9f88-2eaa67143b93 · outbound

This paper cites Frozen clip models are efficient video learners.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Frozen clip models are efficient video learners

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.036110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fdf89e7f-b712-4165-84cc-0524b34cb94b · outbound

This paper cites Revisiting temporal modeling for clip-based image-to-video knowledge transferring.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Revisiting temporal modeling for clip-based image-to-video knowledge transferring

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.020826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 83cf222f-01f6-4fc0-b64d-7d5bc2a43bf3 · outbound

This paper cites Revisiting temporal modeling for clip-based image-to-video knowledge transferring.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Revisiting temporal modeling for clip-based image-to-video knowledge transferring

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:36.002043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5e553e47-f158-4342-b759-54babcbf0257 · outbound

This paper cites Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:34.142444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c08765bf-906b-45d3-8e29-d86035509d44 · outbound

This paper cites Decoupled weight decay regularization.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Decoupled weight decay regularization

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:34.147093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79e3dd92-e866-4dcc-8f9f-485a8a455d83 · outbound

This paper cites Verbs in action: Improv- ing verb understanding in video-language models.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Verbs in action: Improv- ing verb understanding in video-language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.967268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation aa9df3ab-1c93-4e5c-af9e-c2f424e757b2 · outbound

This paper cites Zero-shot temporal action detection via vision-language prompting.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Zero-shot temporal action detection via vision-language prompting

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.953181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0db54a28-09cc-447f-80f8-dedade732fd3 · outbound

This paper cites Zero-shot temporal action detection via vision-language prompting.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Zero-shot temporal action detection via vision-language prompting

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.925219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9944dc8b-70e2-4561-9129-f828df311ed2 · outbound

This paper cites Expanding language-image pretrained models for gen- eral video recognition.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Expanding language-image pretrained models for gen- eral video recognition

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.905040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ebb2f9c1-454b-48a6-9593-05de32ece069 · outbound

This paper cites Expanding language-image pretrained models for gen- eral video recognition.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Expanding language-image pretrained models for gen- eral video recognition

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.886681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d4e87b73-854e-4aee-b8e7-adb107377104 · outbound

This paper cites GPT-4 Technical Report.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection GPT-4 Technical Report

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:34.199421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3da5c551-d16e-4ac1-ae8c-614c9c120058 · outbound

This paper cites Actor-context-actor relation net- work for spatio-temporal action localization.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Actor-context-actor relation net- work for spatio-temporal action localization

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.870041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 81dffbc5-8af5-4945-94d0-0e49a45e975f · outbound

This paper cites St-adapter: Parameter-efficient image-to-video transfer learning.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection St-adapter: Parameter-efficient image-to-video transfer learning

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.854822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b5874fa3-658e-4643-a83d-ff134bca9207 · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Learn- ing transferable visual models from natural language super- vision

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.836146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4d2e88c0-1bb0-42e1-9891-0f9add2444a0 · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Learn- ing transferable visual models from natural language super- vision

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.813548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2aae92bd-2bf9-4752-8b8f-0f0205d3967c · outbound

This paper cites Fine-tuned clip models are efficient video learners.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Fine-tuned clip models are efficient video learners

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.796054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e253c8d0-066f-41b0-9685-f289a970ef83 · outbound

This paper cites Open-vocabulary temporal action detection with off-the-shelf image-text features.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Open-vocabulary temporal action detection with off-the-shelf image-text features

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.780311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 083eb89f-447a-48a8-8054-c1df10550bad · outbound

This paper cites Faster r-cnn: Towards real-time object detection with region proposal networks.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Faster r-cnn: Towards real-time object detection with region proposal networks

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:34.253502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 724675cb-153f-4780-b4b2-a6798463402a · outbound

This paper cites Generalized in- tersection over union: A metric and a loss for bounding box regression.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Generalized in- tersection over union: A metric and a loss for bounding box regression

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:34.257602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59106dfc-b53e-4ec7-88b5-be3eeeb0d5b6 · outbound

This paper cites Sparse DETR: Efficient end-to-end object detec- tion with learnable sparsity.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Sparse DETR: Efficient end-to-end object detec- tion with learnable sparsity

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.743383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f93e6906-a7cc-4ba2-9da8-4af4973beca9 · outbound

This paper cites Hi- era: A hierarchical vision transformer without the bells-and- whistles.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Hi- era: A hierarchical vision transformer without the bells-and- whistles

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.726724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 91d9c389-3853-478b-9aa6-f4b0d78c39f5 · outbound

This paper cites Grad-cam: Visual explanations from deep networks via gradient-based localization.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Grad-cam: Visual explanations from deep networks via gradient-based localization

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.703196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5bdd13fe-1598-41bc-b9a9-e7c8978c548c · outbound

This paper cites Road: The road event awareness dataset for autonomous driving.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Road: The road event awareness dataset for autonomous driving

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.688783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c60eda70-48eb-4399-bea5-d0e95325d959 · outbound

This paper cites Ucf101: A dataset of 101 human actions classes from videos in the wild.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Ucf101: A dataset of 101 human actions classes from videos in the wild

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.670972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9e8d9b78-66a6-4176-b7c2-12f4eb1c56f1 · outbound

This paper cites Actor-centric relation network.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Actor-centric relation network

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.654926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e6691d63-bfe3-4569-b800-587c8c19d26e · outbound

This paper cites Relational action forecasting.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Relational action forecasting

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.620142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2d2becb4-77a4-4488-9e45-fb5cf60f330a · outbound

This paper cites Sparse r-cnn: End-to-end object detec- tion with learnable proposals.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Sparse r-cnn: End-to-end object detec- tion with learnable proposals

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.596591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f3b7da0b-fc8a-4876-8656-6f785bd2d0ec · outbound

This paper cites Asynchronous interaction aggregation for action detection.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Asynchronous interaction aggregation for action detection

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.576476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9b3ac7e4-8a5e-4709-a9a6-a0f99214bebb · outbound

This paper cites Mlp-mixer: An all-mlp architecture for vision.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Mlp-mixer: An all-mlp architecture for vision

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.558998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d4ded328-8ca6-40d1-8e5d-ea4b27506309 · outbound

This paper cites Attention is all you need.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Attention is all you need

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.540707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2862efa0-b746-4ef8-8848-e4580b94e97a · outbound

This paper cites ActionCLIP: A New Paradigm for Video Action Recognition.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection ActionCLIP: A New Paradigm for Video Action Recognition

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:34.333164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cef25c1c-96cf-4f48-a3cf-a785f982f251 · outbound

This paper cites Vita-clip: Video and text adaptive clip via multimodal prompting.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Vita-clip: Video and text adaptive clip via multimodal prompting

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.501357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 49b02c60-0397-4add-bb39-60f46e93c4b0 · outbound

This paper cites Open-vclip: Transforming clip to an open-vocabulary video model via interpolated weight optimization.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Open-vclip: Transforming clip to an open-vocabulary video model via interpolated weight optimization

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.477256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 22930374-aaaa-4cb5-bc82-56616bdefd0b · outbound

This paper cites Long-term feature banks for detailed video understanding.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Long-term feature banks for detailed video understanding

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.460235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 81150c78-644c-49be-82a4-af4bbc0f6241 · outbound

This paper cites Context-aware rcnn: A baseline for ac- tion detection in videos.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Context-aware rcnn: A baseline for ac- tion detection in videos

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.442768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fa01248c-5077-4de8-8e0e-ca3bf8273f72 · outbound

This paper cites Towards Open Vocabulary Learning: A Survey.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Towards Open Vocabulary Learning: A Survey

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:34.355336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 512e006d-b5fa-4039-8c0f-5ce3411677e8 · outbound

This paper cites Stmixer: A one-stage sparse action detector.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Stmixer: A one-stage sparse action detector

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.425422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6ed96869-fb21-4314-ad30-5ee6828fb25e · outbound

This paper cites Stmixer: A one-stage sparse action detector.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Stmixer: A one-stage sparse action detector

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.405882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6228390b-7bcb-49f7-b9e7-eb4aeaf4a8f0 · outbound

This paper cites Open-Vocabulary Spatio-Temporal Action Detection.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Open-Vocabulary Spatio-Temporal Action Detection

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:34.369317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a450ad62-ef08-4428-a427-86f9125e5f3a · outbound

This paper cites Cora: Adapting clip for open-vocabulary detection with region prompting and anchor pre-matching.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Cora: Adapting clip for open-vocabulary detection with region prompting and anchor pre-matching

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.390028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4a15141a-cc08-4019-9d1f-55152793a02b · outbound

This paper cites Clip-vip: Adapting pre- trained image-text model to video-language representation alignment.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Clip-vip: Adapting pre- trained image-text model to video-language representation alignment

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.375890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5576a9a8-ab22-4929-9de9-141a61b7f618 · outbound

This paper cites Clip-vip: Adapting pre- trained image-text model to video-language representation alignment.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Clip-vip: Adapting pre- trained image-text model to video-language representation alignment

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.359394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c1dde812-30d6-474c-a4db-8f8112fc3d92 · outbound

This paper cites Unloc: A unified framework for video localization tasks.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Unloc: A unified framework for video localization tasks

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.342125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6a60e58f-1d3a-480f-ad50-8620f40144e3 · outbound

This paper cites Detecting human actions in surveillance videos.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Detecting human actions in surveillance videos

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.323223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ee6e3520-08f2-4373-9558-c55e4b34417c · outbound

This paper cites Contextualized spatio-temporal contrastive learning with self-supervision.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Contextualized spatio-temporal contrastive learning with self-supervision

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.286810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1a35debf-220f-4151-9dcf-e3d2c372e435 · outbound

This paper cites Vision-based garbage dumping action detection for real-world surveillance platform.ETRI Journal, 41(4):494–505, 2019.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Vision-based garbage dumping action detection for real-world surveillance platform.ETRI Journal, 41(4):494–505, 2019

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.259768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ba00c246-766c-4df0-9b77-2e412d624b1c · outbound

This paper cites Open-vocabulary detr with conditional matching.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Open-vocabulary detr with conditional matching

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.227399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 778c0bbe-b2f3-4369-b6e5-55093f7d3d82 · outbound

This paper cites Open-vocabulary object detection using captions.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Open-vocabulary object detection using captions

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.195512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c3229a69-53c5-4c6a-b995-cd6e3a770985 · outbound

This paper cites Open-vocabulary object detection using captions.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Open-vocabulary object detection using captions

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.168723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f94dff5c-4afc-40ef-b6f8-8bf85f6e1a47 · outbound

This paper cites From recognition to cognition: Visual commonsense reason- ing.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection From recognition to cognition: Visual commonsense reason- ing

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.139140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c2e45b16-72d3-4443-9478-a1e903d3ec23 · outbound

This paper cites Vinvl: Revisiting visual representations in vision-language models.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Vinvl: Revisiting visual representations in vision-language models

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.089742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2316d72b-c42a-4441-a29f-faeed5df7917 · outbound

This paper cites Tuber: Tubelet transformer for video action detection.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Tuber: Tubelet transformer for video action detection

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.065261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fb604aaf-58c5-40a6-8b26-0a72517c0866 · outbound

This paper cites MRSN: Multi-Relation Support Network for Video Action Detection.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection MRSN: Multi-Relation Support Network for Video Action Detection

Reference 92

Resolution: verified exact; local_arxiv, observed 2026-08-12T19:14:34.558149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bf65d351-a680-4c7c-a476-f51acb3f9e45 · outbound

This paper cites Regionclip: Region-based language-image pretraining.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Regionclip: Region-based language-image pretraining

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.040683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8f0230f2-e4ce-4cdc-98e5-cc72b0593fee · outbound

This paper cites Learning deep features for discrimi- native localization.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Learning deep features for discrimi- native localization

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:35.005673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2a8ecf9d-e5b1-4f1f-9cea-074b3d180b78 · outbound

This paper cites Learning to prompt for vision-language models.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Learning to prompt for vision-language models

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:34.482606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d972e5f-770b-48e3-93a5-930a182a96a3 · outbound

This paper cites Zegclip: Towards adapting clip for zero-shot se- mantic segmentation.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection Zegclip: Towards adapting clip for zero-shot se- mantic segmentation

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-12T19:14:34.487802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6347dfc0-d29f-4afe-915d-746364a3c506 · outbound

This paper cites For the action type {CLS}, what are the visual descriptions? Please respond with a list of 16 short sentences.

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection For the action type {CLS}, what are the visual descriptions? Please respond with a list of 16 short sentences

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:14:34.950581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers