Zero-shot 2D Grounding with Novel Affordance Types | Paper Citation Record

Observation 0c90af25-5541-4c4f-9afe-fae9ca250baa · outbound

This paper cites GPT-4 Technical Report.

Zero-shot 2D Grounding with Novel Affordance Types GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-14T04:24:59.589172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffb8cbdb-de47-48cb-bbee-413cbb585b25 · outbound

This paper cites Do as I can, not as I say: Grounding language in robotic affordances.

Zero-shot 2D Grounding with Novel Affordance Types Do as I can, not as I say: Grounding language in robotic affordances

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-14T04:24:59.607413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe0cd259-cc13-4ed5-8fed-b02154ff954f · outbound

This paper cites Affordances from human videos as a versatile representation for robotics.

Zero-shot 2D Grounding with Novel Affordance Types Affordances from human videos as a versatile representation for robotics

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-14T04:24:59.629573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23b284c5-00f8-4172-9801-242bb42dfc63 · outbound

This paper cites ViSPLA: Visual iterative self-prompting for language-guided 3d affordance learning.

Zero-shot 2D Grounding with Novel Affordance Types ViSPLA: Visual iterative self-prompting for language-guided 3d affordance learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-14T04:24:59.639580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68b794f9-1230-4b4f-9797-95df22f12e47 · outbound

This paper cites Grounding everything: Emerging localization properties in vision-language transformers.

Zero-shot 2D Grounding with Novel Affordance Types Grounding everything: Emerging localization properties in vision-language transformers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-14T04:24:59.660952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1bb08ab-4158-4e1c-abac-ec6f5fd4c7de · outbound

This paper cites Language models are few-shot learners.

Zero-shot 2D Grounding with Novel Affordance Types Language models are few-shot learners

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-14T04:24:59.671131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c3749ff-eaf4-40f9-8e1c-5248b0afde54 · outbound

This paper cites Emerging properties in self-supervised vision transformers.

Zero-shot 2D Grounding with Novel Affordance Types Emerging properties in self-supervised vision transformers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-14T04:24:59.699226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbb14ec9-bdfe-4c3a-8abb-8caa484cf3fc · outbound

This paper cites Worldafford: Affordance grounding based on natural language instructions.

Zero-shot 2D Grounding with Novel Affordance Types Worldafford: Affordance grounding based on natural language instructions

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-14T04:24:59.714778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eb42807-225c-4755-b0f1-41c975017b7d · outbound

This paper cites Affordance grounding from demon- stration video to target image.

Zero-shot 2D Grounding with Novel Affordance Types Affordance grounding from demon- stration video to target image

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-14T04:24:59.724265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8bee974-b17c-40ca-b81d-2074d0d2c8e2 · outbound

This paper cites Affordances of augmented reality in science learning: Suggestions for future research.JSET, 2013.

Zero-shot 2D Grounding with Novel Affordance Types Affordances of augmented reality in science learning: Suggestions for future research.JSET, 2013

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-14T04:24:59.736175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2edb4eed-fc01-4e9a-90cb-f03fcdb32235 · outbound

This paper cites 3D- AffordanceLLM: Harnessing large language models for open-vocabulary affordance detection in 3D worlds.

Zero-shot 2D Grounding with Novel Affordance Types 3D- AffordanceLLM: Harnessing large language models for open-vocabulary affordance detection in 3D worlds

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-14T04:24:59.747416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ce199a6-ebeb-46e4-b643-519009b7ee28 · outbound

This paper cites Learning to act properly: Predicting and explaining affordances from images.

Zero-shot 2D Grounding with Novel Affordance Types Learning to act properly: Predicting and explaining affordances from images

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.455761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6d80767d-3bb2-45d7-bb63-412c03ab1850 · outbound

This paper cites A deep multi-level network for saliency prediction.

Zero-shot 2D Grounding with Novel Affordance Types A deep multi-level network for saliency prediction

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.421877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ed81b43f-696c-4537-868a-04b6607701d0 · outbound

This paper cites STRAP: Structured Object Affordance Segmentation with Point Supervision.

Zero-shot 2D Grounding with Novel Affordance Types STRAP: Structured Object Affordance Segmentation with Point Supervision

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-14T04:24:59.815513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 266f2f7b-6fe7-46e6-a206-4be252bbc467 · outbound

This paper cites What does CLIP know about peeling a banana? InCVPRW, 2024.

Zero-shot 2D Grounding with Novel Affordance Types What does CLIP know about peeling a banana? InCVPRW, 2024

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.394149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4ecb9732-2eca-4f63-a2c3-04eaf8b5602f · outbound

This paper cites Decoupling zero-shot semantic segmentation.

Zero-shot 2D Grounding with Novel Affordance Types Decoupling zero-shot semantic segmentation

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.368992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ecb468b9-9766-4b73-ae85-401b1069ec29 · outbound

This paper cites Affordancenet: An end-to-end deep learning approach for object affordance detection.

Zero-shot 2D Grounding with Novel Affordance Types Affordancenet: An end-to-end deep learning approach for object affordance detection

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.346232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 974ec29b-a2c0-4b7a-92cb-b0cefdc6eb0b · outbound

This paper cites Demo2vec: Reasoning object affordances from online videos.

Zero-shot 2D Grounding with Novel Affordance Types Demo2vec: Reasoning object affordances from online videos

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.319488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fce38ab4-ba7f-492a-8419-0f7312117c9c · outbound

This paper cites Learning 2d invariant affordance knowledge for 3d affordance grounding.

Zero-shot 2D Grounding with Novel Affordance Types Learning 2d invariant affordance knowledge for 3d affordance grounding

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.291383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8dee3e03-7c6a-4b7d-b9d5-5428ca1d3633 · outbound

This paper cites RLAfford: End-to-end affordance learning for robotic manipulation.

Zero-shot 2D Grounding with Novel Affordance Types RLAfford: End-to-end affordance learning for robotic manipulation

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.269011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5ecbf72f-697b-4a53-8730-7a0f6dd58da5 · outbound

This paper cites Psychology press, 2014.

Zero-shot 2D Grounding with Novel Affordance Types Psychology press, 2014

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.244381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9055706a-76f8-4c06-a3e7-190cdaa511f8 · outbound

This paper cites One-shot transfer of affordance regions? AffCorrs! InCORL, 2023.

Zero-shot 2D Grounding with Novel Affordance Types One-shot transfer of affordance regions? AffCorrs! InCORL, 2023

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.225469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1338fa03-b532-4531-afb2-3883fe4f9fa2 · outbound

This paper cites Visual affordance and function understanding: A survey.ACM Comput.

Zero-shot 2D Grounding with Novel Affordance Types Visual affordance and function understanding: A survey.ACM Comput

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.205296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 696cf7c6-7498-4d9e-96c0-7e7c6b8bf271 · outbound

This paper cites V oxPoser: Composable 3d value maps for robotic manipulation with language models.

Zero-shot 2D Grounding with Novel Affordance Types V oxPoser: Composable 3d value maps for robotic manipulation with language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.181681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8afe09d7-64f5-4769-9826-c4dd0ccaf300 · outbound

This paper cites Predicting gaze in egocentric video by learning task-dependent attention transition.

Zero-shot 2D Grounding with Novel Affordance Types Predicting gaze in egocentric video by learning task-dependent attention transition

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.162315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d77cd2e8-baa3-44f6-bb7d-a6c4d9296112 · outbound

This paper cites Resource-efficient affordance grounding with complementary depth and semantic prompts.

Zero-shot 2D Grounding with Novel Affordance Types Resource-efficient affordance grounding with complementary depth and semantic prompts

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.139856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 41113a67-6034-4ecc-a46c-cf2baf41062a · outbound

This paper cites Intra: Interaction relationship-aware weakly supervised affordance grounding.

Zero-shot 2D Grounding with Novel Affordance Types Intra: Interaction relationship-aware weakly supervised affordance grounding

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.111039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a8063a6b-c54a-4461-b66d-ae70e69e6010 · outbound

This paper cites One-shot affordance grounding of deformable objects in egocentric organizing scenes.

Zero-shot 2D Grounding with Novel Affordance Types One-shot affordance grounding of deformable objects in egocentric organizing scenes

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.085140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 069f8cf6-52a9-4ca3-a88d-b6fc1a73c009 · outbound

This paper cites AffordanceSAM: Segment Anything Once More in Affordance Grounding.

Zero-shot 2D Grounding with Novel Affordance Types AffordanceSAM: Segment Anything Once More in Affordance Grounding

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:00.117551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c2d24dd-b6b9-44b2-994f-5eed7e51d2ab · outbound

This paper cites Robo-ABC: Affordance generalization beyond categories via semantic correspondence for robot manipulation.

Zero-shot 2D Grounding with Novel Affordance Types Robo-ABC: Affordance generalization beyond categories via semantic correspondence for robot manipulation

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.063034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a8fc2d26-ffa8-409c-a314-574d7f92b23b · outbound

This paper cites Learning human activities and object affordances from RGB-D videos.IJRR, 2013.

Zero-shot 2D Grounding with Novel Affordance Types Learning human activities and object affordances from RGB-D videos.IJRR, 2013

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.043412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1f416183-2019-417f-8be2-bb2b91c46302 · outbound

This paper cites DeepGaze II: Reading fixations from deep features trained on object recognition.

Zero-shot 2D Grounding with Novel Affordance Types DeepGaze II: Reading fixations from deep features trained on object recognition

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:00.162142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe4e2f45-a73d-4c39-9e79-7df70dfc710b · outbound

This paper cites ClearCLIP: Decomposing CLIP representations for dense vision-language inference.

Zero-shot 2D Grounding with Novel Affordance Types ClearCLIP: Decomposing CLIP representations for dense vision-language inference

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:04.018396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ea1242d4-0579-4661-93f1-9a8437735c5f · outbound

This paper cites ProxyCLIP: Proxy attention improves CLIP for open-vocabulary segmentation.

Zero-shot 2D Grounding with Novel Affordance Types ProxyCLIP: Proxy attention improves CLIP for open-vocabulary segmentation

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.993343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 88823012-5ebb-44ea-b452-064d7e7c13c1 · outbound

This paper cites Locate: Localize and transfer object parts for weakly supervised affordance grounding.

Zero-shot 2D Grounding with Novel Affordance Types Locate: Localize and transfer object parts for weakly supervised affordance grounding

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.964683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 717cf55a-8fc6-4e78-97b0-c0357274bca9 · outbound

This paper cites One-shot open affordance learning with foundation models.

Zero-shot 2D Grounding with Novel Affordance Types One-shot open affordance learning with foundation models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.943445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7c668544-b42e-4d63-9e52-ec4530d04b41 · outbound

This paper cites Learning precise affordances from egocentric videos for robotic manipulation.

Zero-shot 2D Grounding with Novel Affordance Types Learning precise affordances from egocentric videos for robotic manipulation

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.897907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fb7d6d82-20ea-4c99-aee4-86feb5326e8f · outbound

This paper cites Adapting CLIP For Phrase Localization Without Further Training.

Zero-shot 2D Grounding with Novel Affordance Types Adapting CLIP For Phrase Localization Without Further Training

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:00.259046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11a4de50-1644-45f4-a37c-90027f578fe3 · outbound

This paper cites Laso: Language-guided affordance segmentation on 3d object.

Zero-shot 2D Grounding with Novel Affordance Types Laso: Language-guided affordance segmentation on 3d object

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.832024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4bad5a48-78e9-4c7a-b470-29d334b2bc85 · outbound

This paper cites Intermediate connectors and geometric priors for language-guided affordance segmentation on unseen object categories.

Zero-shot 2D Grounding with Novel Affordance Types Intermediate connectors and geometric priors for language-guided affordance segmentation on unseen object categories

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.788525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9901d814-d276-4c26-ad2b-30f811338d11 · outbound

This paper cites Grounding DINO: Marrying dino with grounded pre-training for open-set object detection.

Zero-shot 2D Grounding with Novel Affordance Types Grounding DINO: Marrying dino with grounded pre-training for open-set object detection

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.705858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bf42f043-7aa5-4f92-b070-ea919fe9bf30 · outbound

This paper cites GEAL: Generalizable 3d affordance learning with cross-modal consistency.

Zero-shot 2D Grounding with Novel Affordance Types GEAL: Generalizable 3d affordance learning with cross-modal consistency

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.652879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 581e08ba-5788-4952-80d3-417faf767293 · outbound

This paper cites Learning affordance grounding from exocentric images.

Zero-shot 2D Grounding with Novel Affordance Types Learning affordance grounding from exocentric images

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.590463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f1e673d4-e3a6-4457-9025-ee5f77f96698 · outbound

This paper cites Learning visual affordance grounding from demonstration videos.IEEE TNNLS, 2023.

Zero-shot 2D Grounding with Novel Affordance Types Learning visual affordance grounding from demonstration videos.IEEE TNNLS, 2023

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.539167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2c96f9b2-4427-4dab-816f-ab81e9a0a929 · outbound

This paper cites Grounding language with visual affordances over unstructured data.

Zero-shot 2D Grounding with Novel Affordance Types Grounding language with visual affordances over unstructured data

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.458647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b2811bba-d493-429c-a951-b4621a4e411a · outbound

This paper cites LAN-grasp: Using large language models for semantic object grasping.arXiv preprint arXiv:2310.05239, 2023.

Zero-shot 2D Grounding with Novel Affordance Types LAN-grasp: Using large language models for semantic object grasping.arXiv preprint arXiv:2310.05239, 2023

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:00.446329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55fd075d-04e4-4681-8e1d-72fd0f046240 · outbound

This paper cites Embodied large language models enable robots to complete complex tasks in unpredictable environments.Nature Machine Intelligence,.

Zero-shot 2D Grounding with Novel Affordance Types Embodied large language models enable robots to complete complex tasks in unpredictable environments.Nature Machine Intelligence,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.427235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7b49a9e5-a562-464a-b016-ff8b8eab7380 · outbound

This paper cites Selective contrastive learning for weakly supervised affordance grounding.

Zero-shot 2D Grounding with Novel Affordance Types Selective contrastive learning for weakly supervised affordance grounding

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.381372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1fda5415-2668-4c8c-82c8-cc1eb0514a8a · outbound

This paper cites Affordance detection of tool parts from geometric features.

Zero-shot 2D Grounding with Novel Affordance Types Affordance detection of tool parts from geometric features

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.338340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d7d621d1-3dfe-4c2a-a7d7-0f8d9d9d162a · outbound

This paper cites Learning affordance landscapes for interaction exploration in 3d environments.

Zero-shot 2D Grounding with Novel Affordance Types Learning affordance landscapes for interaction exploration in 3d environments

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.285818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b66f641f-5f02-4c85-84e5-217868f73f40 · outbound

This paper cites Grounded human-object interaction hotspots from video.

Zero-shot 2D Grounding with Novel Affordance Types Grounded human-object interaction hotspots from video

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.251898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d5ceb384-9d79-4876-b5ab-59d7f659f765 · outbound

This paper cites Caldwell, and Nikos G.

Zero-shot 2D Grounding with Novel Affordance Types Caldwell, and Nikos G

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.158122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 58a8a30f-3057-4048-825a-23e78d2b1b7c · outbound

This paper cites Open- vocabulary affordance detection in 3d point clouds.

Zero-shot 2D Grounding with Novel Affordance Types Open- vocabulary affordance detection in 3d point clouds

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.110999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 894e5207-7a1d-4989-a586-b5d9dbfba7cd · outbound

This paper cites Introducing GPT-5.2.

Zero-shot 2D Grounding with Novel Affordance Types Introducing GPT-5.2

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.072306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0372b1e9-6604-4ad0-aca5-34072ec1097a · outbound

This paper cites Dinov2: Learning robust visual features without supervision.TMLR, 2024.

Zero-shot 2D Grounding with Novel Affordance Types Dinov2: Learning robust visual features without supervision.TMLR, 2024

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:03.044033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b8aef135-de32-4821-bdbb-e29dd231fe13 · outbound

This paper cites SalGAN: Visual Saliency Prediction with Generative Adversarial Networks.

Zero-shot 2D Grounding with Novel Affordance Types SalGAN: Visual Saliency Prediction with Generative Adversarial Networks

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:00.638291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbeeb65e-8ca6-4bbb-bc35-f259f2255f31 · outbound

This paper cites AffordanceLLM: Grounding affordance from vision language models.

Zero-shot 2D Grounding with Novel Affordance Types AffordanceLLM: Grounding affordance from vision language models

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.989761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b3abf650-1e3a-4a6f-a703-9141e30b5949 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Zero-shot 2D Grounding with Novel Affordance Types Learning transferable visual models from natural language supervision

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.942168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8216afe2-d635-4de2-a23e-9a6004cc7b97 · outbound

This paper cites Strategies to leverage foundational model knowledge in object affordance grounding.

Zero-shot 2D Grounding with Novel Affordance Types Strategies to leverage foundational model knowledge in object affordance grounding

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.880344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d238b413-a0d4-45ed-8222-bede1fb6057a · outbound

This paper cites Language embedded radiance fields for zero-shot task-oriented grasping.

Zero-shot 2D Grounding with Novel Affordance Types Language embedded radiance fields for zero-shot task-oriented grasping

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.838191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c6fb0534-4c8a-4309-a618-ee395027411f · outbound

This paper cites SAM 2: Segment Anything in Images and Videos.

Zero-shot 2D Grounding with Novel Affordance Types SAM 2: Segment Anything in Images and Videos

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:00.724745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 466fbedd-f008-48b2-bebb-0d918cc03175 · outbound

This paper cites Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks.

Zero-shot 2D Grounding with Novel Affordance Types Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:00.735823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efb000cc-f37c-4718-897f-f379f14627dc · outbound

This paper cites Adaptive binarization for weakly supervised affordance segmentation.

Zero-shot 2D Grounding with Novel Affordance Types Adaptive binarization for weakly supervised affordance segmentation

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.775254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ad19fbfd-b14c-41c3-9661-f1c41da11300 · outbound

This paper cites Weakly supervised affordance detection.

Zero-shot 2D Grounding with Novel Affordance Types Weakly supervised affordance detection

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.709743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 76e1712d-49c6-4266-a588-5132fd5876d7 · outbound

This paper cites GREAT: Geometry- intention collaborative inference for open-vocabulary 3d object affordance grounding.

Zero-shot 2D Grounding with Novel Affordance Types GREAT: Geometry- intention collaborative inference for open-vocabulary 3d object affordance grounding

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.671657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a1413b01-06c7-434f-861e-c33a84e8879e · outbound

This paper cites Learning 6-DoF fine-grained grasp detection based on part affordance grounding.IEEE TASE, 2025.

Zero-shot 2D Grounding with Novel Affordance Types Learning 6-DoF fine-grained grasp detection based on part affordance grounding.IEEE TASE, 2025

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.635005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cfcf9a7b-96a8-439d-b112-278c5315f6e6 · outbound

This paper cites Closed-loop transfer for weakly-supervised affordance grounding.

Zero-shot 2D Grounding with Novel Affordance Types Closed-loop transfer for weakly-supervised affordance grounding

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.569620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9a6c3ebd-c770-4d16-8fd8-94b765482766 · outbound

This paper cites Oval-prompt: Open-vocabulary affordance localization for robot manipulation through llm affordance-grounding.

Zero-shot 2D Grounding with Novel Affordance Types Oval-prompt: Open-vocabulary affordance localization for robot manipulation through llm affordance-grounding

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.534748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bc248883-96b6-426d-b370-e525a78a90a4 · outbound

This paper cites Open- vocabulary affordance detection using knowledge distillation and text-point correlation.

Zero-shot 2D Grounding with Novel Affordance Types Open- vocabulary affordance detection using knowledge distillation and text-point correlation

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.484155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 22bb1560-6d74-4eaf-a88e-74b28cbf8fce · outbound

This paper cites Attention is all you need.

Zero-shot 2D Grounding with Novel Affordance Types Attention is all you need

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:00.839548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb84c558-8e93-468b-96e5-a2ffb8a9ec67 · outbound

This paper cites Predicting actions from static scenes.

Zero-shot 2D Grounding with Novel Affordance Types Predicting actions from static scenes

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.450212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cf155cb5-7662-440b-a49e-c9656041579e · outbound

This paper cites SCLIP: Rethinking self-attention for dense vision-language inference.

Zero-shot 2D Grounding with Novel Affordance Types SCLIP: Rethinking self-attention for dense vision-language inference

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.431152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 20b0ec59-60b8-4539-9009-a7083908b3fc · outbound

This paper cites AffordDexGrasp: Open-set language-guided dexterous grasp with generalizable-instructive affordance.

Zero-shot 2D Grounding with Novel Affordance Types AffordDexGrasp: Open-set language-guided dexterous grasp with generalizable-instructive affordance

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.397587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7136222f-54d2-478b-8a8b-14dad5f4ebfd · outbound

This paper cites 3DAffordSplat: Efficient affordance reasoning with 3d gaussians.

Zero-shot 2D Grounding with Novel Affordance Types 3DAffordSplat: Efficient affordance reasoning with 3d gaussians

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.368835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 47b4a63c-193a-4925-ae9e-192c5160731c · outbound

This paper cites RAGNet: Large-scale reasoning-based affordance segmentation benchmark towards general grasping.

Zero-shot 2D Grounding with Novel Affordance Types RAGNet: Large-scale reasoning-based affordance segmentation benchmark towards general grasping

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.349843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8ded06cf-29b4-47af-94c5-af6ff16f42d4 · outbound

This paper cites Towards open vocabulary learning: A survey.IEEE TPAMI, 2024.

Zero-shot 2D Grounding with Novel Affordance Types Towards open vocabulary learning: A survey.IEEE TPAMI, 2024

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.327991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0d78e3f5-6bba-4e70-ba61-da8dc89712cd · outbound

This paper cites Florence-2: Advancing a unified representation for a variety of vision tasks.

Zero-shot 2D Grounding with Novel Affordance Types Florence-2: Advancing a unified representation for a variety of vision tasks

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.295909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 63b16190-3e95-4fbf-9766-b36ed82a104f · outbound

This paper cites SED: A simple encoder-decoder for open-vocabulary semantic segmentation.

Zero-shot 2D Grounding with Novel Affordance Types SED: A simple encoder-decoder for open-vocabulary semantic segmentation

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.254103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0daa9bcb-86db-45a3-88b5-7ab313fb2462 · outbound

This paper cites Weakly supervised multimodal affordance grounding for egocentric images.

Zero-shot 2D Grounding with Novel Affordance Types Weakly supervised multimodal affordance grounding for egocentric images

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.189132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a1ec0b89-792a-4008-b47f-91162fe68e30 · outbound

This paper cites Side adapter network for open- vocabulary semantic segmentation.

Zero-shot 2D Grounding with Novel Affordance Types Side adapter network for open- vocabulary semantic segmentation

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.159291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 27cbced3-9dce-4459-8fbb-2e036679ab1e · outbound

This paper cites Weakly-supervised affordance grounding guided by part-level semantic priors.

Zero-shot 2D Grounding with Novel Affordance Types Weakly-supervised affordance grounding guided by part-level semantic priors

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.138652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 82fa5d50-2dfc-4f34-bf10-719899c24b54 · outbound

This paper cites Universal instance perception as object discovery and retrieval.

Zero-shot 2D Grounding with Novel Affordance Types Universal instance perception as object discovery and retrieval

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.066019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9afb80b5-1bbd-48d9-8eab-92922c4008d1 · outbound

This paper cites Grounding 3d object affordance from 2d interactions in images.

Zero-shot 2D Grounding with Novel Affordance Types Grounding 3d object affordance from 2d interactions in images

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.042436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e3e6d444-088e-479b-a857-563374124ff0 · outbound

This paper cites 2HandedAf- forder: Learning precise actionable bimanual affordances from human videos.

Zero-shot 2D Grounding with Novel Affordance Types 2HandedAf- forder: Learning precise actionable bimanual affordances from human videos

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:02.019717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fc099bc0-0d00-4d4c-8125-fc09cda77009 · outbound

This paper cites SeqAfford: Sequential 3d affordance reasoning via multimodal large language model.

Zero-shot 2D Grounding with Novel Affordance Types SeqAfford: Sequential 3d affordance reasoning via multimodal large language model

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:01.989262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 47122d56-c38e-4198-99ca-dc93fafc72f0 · outbound

This paper cites One-shot object affordance detection in the wild.IJCV, 2022.

Zero-shot 2D Grounding with Novel Affordance Types One-shot object affordance detection in the wild.IJCV, 2022

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:01.957879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 06616474-0615-4f3c-be51-94f5a12d8657 · outbound

This paper cites Extract free dense labels from CLIP.

Zero-shot 2D Grounding with Novel Affordance Types Extract free dense labels from CLIP

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:01.921563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3a2af93c-1d6e-4796-9a49-257bbb3cf77f · outbound

This paper cites ZegClip: Towards adapting CLIP for zero-shot semantic segmentation.

Zero-shot 2D Grounding with Novel Affordance Types ZegClip: Towards adapting CLIP for zero-shot semantic segmentation

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:01.855261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 442314b8-6c99-41ad-a706-3b0d1334788c · outbound

This paper cites Grounding 3d object affordance with language instructions, visual observations and interactions.

Zero-shot 2D Grounding with Novel Affordance Types Grounding 3d object affordance with language instructions, visual observations and interactions

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:01.806178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a7397722-d4ad-47d4-86dc-0a4b6b25fb7d · outbound

This paper cites Seen” and “Unseen.

Zero-shot 2D Grounding with Novel Affordance Types Seen” and “Unseen

Reference 2025

Resolution: verified exact; raw_fallback, observed 2026-08-14T04:25:01.372600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers