AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction | Paper Citation Record

Observation 95410f75-ccf0-4bc0-a682-563d866b901d · outbound

This paper cites Keyformer: Kv cache reduction through key tokens selection for efficient generative inference.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Keyformer: Kv cache reduction through key tokens selection for efficient generative inference

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.279414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3d9d42e9-f402-4e97-bc93-0c5f8c977a79 · outbound

This paper cites Visual question an- swering, 2015.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Visual question an- swering, 2015

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.267667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d061cf7e-d4fa-4cf3-b2d0-a8356d2579db · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Flamingo: a visual language model for few-shot learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.337833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b99d0214-6897-4263-8098-8ec517658b96 · outbound

This paper cites METEOR: An auto- matic metric for MT evaluation with improved correlation with human judgments.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction METEOR: An auto- matic metric for MT evaluation with improved correlation with human judgments

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.343027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55fec8ff-e7a7-42be-a98c-2e3885118bba · outbound

This paper cites Language Models are Few-Shot Learners.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Language Models are Few-Shot Learners

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.347320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd5716e1-3e86-4639-b831-6149ab187301 · outbound

This paper cites Chen and William B.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Chen and William B

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.241155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation eb0fdabb-c8b5-4f57-abb8-1920dce53d98 · outbound

This paper cites Videollm-online: Online video large language model for streaming video.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Videollm-online: Online video large language model for streaming video

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.226887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6013e716-7fca-49dd-bb7c-1867de592ef4 · outbound

This paper cites Gonzalez, Ion Stoica, and Eric P.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Gonzalez, Ion Stoica, and Eric P

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.213152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 66ad7158-bae8-4ee9-bb25-68dc384440cf · outbound

This paper cites Rethinking Attention with Performers.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Rethinking Attention with Performers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.366010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f41f1ff-e22a-43d4-9a83-7a60f7d4d602 · outbound

This paper cites Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.198912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a505b763-7b73-4d92-8951-1ce2e913d1ba · outbound

This paper cites Instructblip: Towards general-purpose vision-language models with instruction tuning, 2023.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Instructblip: Towards general-purpose vision-language models with instruction tuning, 2023

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.182886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6689eded-43e4-4b39-9861-ebc55cf1cfcf · outbound

This paper cites Visual question answering: A survey on techniques and common trends in recent literature, 2023.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Visual question answering: A survey on techniques and common trends in recent literature, 2023

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.170278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 09b7155f-029e-4c6e-8626-b2e0e25d88b5 · outbound

This paper cites Im- pact of green human resource management (ghrm) practices on organizational performance.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Im- pact of green human resource management (ghrm) practices on organizational performance

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.157152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a153acce-fca9-4ca1-b53d-7701cea2bc61 · outbound

This paper cites Model tells you what to dis- card: Adaptive KV cache compression for LLMs.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Model tells you what to dis- card: Adaptive KV cache compression for LLMs

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.145790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7611fc79-9f75-432a-a42f-31e24613990b · outbound

This paper cites Ego4d: Around the world in 3,000 hours of egocentric video.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Ego4d: Around the world in 3,000 hours of egocentric video

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.389678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b57164a6-e681-43d6-a38a-5f2995b73726 · outbound

This paper cites Ma-lmm: Memory-augmented large multimodal model for long-term video understanding.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Ma-lmm: Memory-augmented large multimodal model for long-term video understanding

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.127218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6e71ec0a-51d6-48fc-9536-b39f3988c980 · outbound

This paper cites an unresolved cited work.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-12T17:18:53.114321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2f81c3c2-6582-4a9f-aa3b-dab495207558 · outbound

This paper cites an unresolved cited work.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-12T17:18:53.100621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 94794bb2-b37c-42a2-917c-c7035592f231 · outbound

This paper cites Long Movie Clip Classification with State-Space Video Models.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Long Movie Clip Classification with State-Space Video Models

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-12T17:18:52.696425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 91410906-4c72-4183-9d38-0c265dcd6ed8 · outbound

This paper cites Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.412135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f741578-4054-4cd9-8acf-f7168886f12f · outbound

This paper cites Kuehne, A.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Kuehne, A

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.085920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fb7e2a55-122b-424a-afe4-bb892213d4bb · outbound

This paper cites Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.422734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b12c74e-bce0-4c6e-9be8-3a0251bff48f · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models, 2023.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models, 2023

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.068418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 66babe02-ab24-4c5d-b0fb-fce9938a2204 · outbound

This paper cites Swinbert: End-to-end transformers with sparse attention for video cap- tioning, 2022.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Swinbert: End-to-end transformers with sparse attention for video cap- tioning, 2022

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.055301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6d31e14a-4413-4cfe-8992-22ece5de9a18 · outbound

This paper cites Learning to recognize procedural activities with distant supervision.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Learning to recognize procedural activities with distant supervision

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.040153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation aea4ce7f-9553-4caa-a556-7dc4e9212327 · outbound

This paper cites Minicache: Kv cache com- pression in depth dimension for large language models.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Minicache: Kv cache com- pression in depth dimension for large language models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.027625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 65910ce0-ec8e-4968-afa0-be4568b96b69 · outbound

This paper cites Vil- bert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Vil- bert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:53.013773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ecee83cb-8a8d-4eeb-81ca-8fa4ceac7922 · outbound

This paper cites Univl: A unified video and language pre-training model for multimodal understanding and generation, 2020.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Univl: A unified video and language pre-training model for multimodal understanding and generation, 2020

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.997496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 075d7e8d-422a-45b4-a6c6-f24acd4974da · outbound

This paper cites Howto100m: Learning a text-video embedding by watching hundred mil- lion narrated video clips.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Howto100m: Learning a text-video embedding by watching hundred mil- lion narrated video clips

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.981415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7492252c-79da-4045-be69-edd961913d41 · outbound

This paper cites GPT-4 Technical Report.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction GPT-4 Technical Report

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.460526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8217b22-e0ba-4cb3-ae3d-0647861bbe59 · outbound

This paper cites Training language models to follow instructions with human feedback.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Training language models to follow instructions with human feedback

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.464083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72fea359-d661-4c8d-ab36-520cfa98c52d · outbound

This paper cites Keeping your eye on the ball: Tra- jectory attention in video transformers.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Keeping your eye on the ball: Tra- jectory attention in video transformers

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.469522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56c991cf-ec6c-4fcb-8895-cd15d0bd106f · outbound

This paper cites EVA-CLIP: Improved Training Techniques for CLIP at Scale.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction EVA-CLIP: Improved Training Techniques for CLIP at Scale

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.473471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4133aced-a1b2-492c-b9e7-5279d56d9b51 · outbound

This paper cites Language models are unsuper- vised multitask learners.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Language models are unsuper- vised multitask learners

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.963845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7b98fb64-484c-49ba-9865-0d3af1ea7b2b · outbound

This paper cites Moviechat: From dense token to sparse memory for long video understanding.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Moviechat: From dense token to sparse memory for long video understanding

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.483532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3b4c4f3-f47a-4e99-aecd-871d1b2de118 · outbound

This paper cites VideoBERT: A Joint Model for Video and Language Representation Learning.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction VideoBERT: A Joint Model for Video and Language Representation Learning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.489724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3e5e8fc-7a81-4004-ba67-7218589bec66 · outbound

This paper cites Plummer, Bryan Russell, and Kate Saenko.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Plummer, Bryan Russell, and Kate Saenko

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.946562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0b872129-f3a2-498d-8e96-d1a7efca6d50 · outbound

This paper cites Coin: A large-scale dataset for comprehensive instructional video analysis.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Coin: A large-scale dataset for comprehensive instructional video analysis

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.932846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2a97bc42-4581-462b-bfed-7a8a149d692e · outbound

This paper cites Llama: Open and efficient foundation lan- guage models, 2023.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Llama: Open and efficient foundation lan- guage models, 2023

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.919833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 894dcfd0-3ec2-4ef6-9207-e8d736315a54 · outbound

This paper cites CIDEr: Consensus-based Image Description Evaluation.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction CIDEr: Consensus-based Image Description Evaluation

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.506611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de244629-3e21-438e-baa8-6cba81bd515a · outbound

This paper cites Git: A generative image-to-text transformer for vision and language, 2022.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Git: A generative image-to-text transformer for vision and language, 2022

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.909115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7714a6ad-3b9d-4ccc-8727-cf6881322b8d · outbound

This paper cites Selective structured state-spaces for long-form video understanding.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Selective structured state-spaces for long-form video understanding

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.897742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7f0e9205-dc34-4621-ab15-816f2b720674 · outbound

This paper cites Selective structured state-spaces for long-form video understanding.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Selective structured state-spaces for long-form video understanding

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.520356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d4e1cc1-1f14-423f-b893-7fca84a06a2a · outbound

This paper cites Temporal segment networks for action recognition in videos, 2017.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Temporal segment networks for action recognition in videos, 2017

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.876048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7ac3aaf5-c131-4121-81f9-b70d974197cd · outbound

This paper cites Towards Long- Form Video Understanding.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Towards Long- Form Video Understanding

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.863050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 03a8e9b9-470b-4925-95b9-42734523eb9f · outbound

This paper cites Efficient streaming language models with attention sinks.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Efficient streaming language models with attention sinks

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.852767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5db191bf-582b-42a4-aae7-78b4d46c826c · outbound

This paper cites mplug-2: A modularized multi-modal foundation model across text, image and video, 2023.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction mplug-2: A modularized multi-modal foundation model across text, image and video, 2023

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.841104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c07de36d-fa67-4162-94ed-11b3435b0afe · outbound

This paper cites Msr-vtt: A large video description dataset for bridging video and language.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Msr-vtt: A large video description dataset for bridging video and language

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.829041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7e9436db-1f67-4dac-b7ed-f23d50b24f5d · outbound

This paper cites Videococa: Video- text modeling with zero-shot transfer from contrastive cap- tioners, 2023.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Videococa: Video- text modeling with zero-shot transfer from contrastive cap- tioners, 2023

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.816592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 407d2704-b126-4b9a-b957-b6880cc39b26 · outbound

This paper cites Stacked attention networks for image question answering.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Stacked attention networks for image question answering

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.804610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2857f9ec-ec6f-45bd-953d-08344b617ec9 · outbound

This paper cites Scaling vision transformers, 2022.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Scaling vision transformers, 2022

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.793904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0333f01d-dfe9-4fb5-89eb-902d1b851174 · outbound

This paper cites Video-llama: An instruction-tuned audio-visual language model for video un- derstanding, 2023.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Video-llama: An instruction-tuned audio-visual language model for video un- derstanding, 2023

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.780995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a3e1a175-0111-4a5d-83e1-c1902a5a5706 · outbound

This paper cites Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-12T17:18:52.556066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a73a199a-10d1-476b-ac92-6badf7163f57 · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction H2o: Heavy-hitter oracle for efficient generative inference of large language models

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.767157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fd4519f6-10fb-4168-bcd2-244b465266f9 · outbound

This paper cites Towards automatic learning of procedures from web instructional videos.

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction Towards automatic learning of procedures from web instructional videos

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:18:52.752733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers