CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition | Paper Citation Record

Observation 6446068b-9e34-46da-863a-200742939566 · outbound

This paper cites Vu: Edge computing-enabled video usefulness detection and its application in large-scale video surveillance systems,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Vu: Edge computing-enabled video usefulness detection and its application in large-scale video surveillance systems,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:41.091673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ce831a05-68bd-4a0a-a1f0-4452f79e0f5e · outbound

This paper cites Strack: Robust tracking of small objects in low-light conditions,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Strack: Robust tracking of small objects in low-light conditions,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:41.081127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation aa017a64-7f5d-47e8-badd-372457076fed · outbound

This paper cites Ai-driven salient soc- cer events recognition framework for next-generation iot-enabled environments,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Ai-driven salient soc- cer events recognition framework for next-generation iot-enabled environments,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:41.070793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 489c6eb2-a67e-4f79-9813-2dc873cac505 · outbound

This paper cites Contactless patient care using hospital iot: Cctv-camera-based physiological monitoring in icu,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Contactless patient care using hospital iot: Cctv-camera-based physiological monitoring in icu,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:41.060164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7f4c3b93-3727-45f8-97f0-411502ac4afc · outbound

This paper cites Optimization for short video propagation based on user interaction analysis in edge networks,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Optimization for short video propagation based on user interaction analysis in edge networks,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:41.049380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5641c2eb-0d0e-484a-9bc2-6e31e5cff03f · outbound

This paper cites Panacea+: Panoramic and con- trollable video generation for autonomous driving,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Panacea+: Panoramic and con- trollable video generation for autonomous driving,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:41.038910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 825c093c-b36f-477d-9b78-c422c4a7b4cb · outbound

This paper cites Tracenet: A novel modular frame- work for robust multi-object tracking in crowded and dynamic environments,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Tracenet: A novel modular frame- work for robust multi-object tracking in crowded and dynamic environments,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:41.028248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3ec1f5fc-3d76-4fe4-9268-6e610af93803 · outbound

This paper cites Hamot: A hierarchical adaptive framework for robust multi-object tracking in complex environments,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Hamot: A hierarchical adaptive framework for robust multi-object tracking in complex environments,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:41.016711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6b0a8d14-7003-4e49-ab4f-41958b95d69c · outbound

This paper cites Imagenet classifi- cation with deep convolutional neural networks,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Imagenet classifi- cation with deep convolutional neural networks,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:41.006540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1b672238-dcfa-4771-92ed-e303f32fa285 · outbound

This paper cites Facelivt: Face recognition using linear vision transformer with structural reparameterization for mobile device,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Facelivt: Face recognition using linear vision transformer with structural reparameterization for mobile device,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.996640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation aba0f7d5-da88-4d41-8800-d78c7bbcb1e0 · outbound

This paper cites Facelivtv2: An improved hybrid architecture for efficient mobile face recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Facelivtv2: An improved hybrid architecture for efficient mobile face recognition,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.986791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d4e927d7-c21b-4282-aa1c-e235fa952a32 · outbound

This paper cites Video analytics for detecting motorcy- clist helmet rule violations,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Video analytics for detecting motorcy- clist helmet rule violations,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.976884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 115cada3-891f-4498-be39-4a779f6fad24 · outbound

This paper cites Smiletrack: Similarity learning for occlusion-aware multiple object tracking,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Smiletrack: Similarity learning for occlusion-aware multiple object tracking,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.966465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 25b79e1e-d969-478c-a333-1a8b44984e81 · outbound

This paper cites Lighttrack-reid: A lightweight and occlusion-robust framework for multi-object tracking,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Lighttrack-reid: A lightweight and occlusion-robust framework for multi-object tracking,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.956229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 07a36462-cc76-463d-bd06-260ce87bd08d · outbound

This paper cites Ssp-sam: Sam with semantic- spatial prompt for referring expression segmentation,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Ssp-sam: Sam with semantic- spatial prompt for referring expression segmentation,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.945255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8615bf5f-10dd-46d8-89f3-c23fc20a300f · outbound

This paper cites UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T22:27:40.117497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a7efa79-b9ab-498f-91ff-58d8ccba52e3 · outbound

This paper cites The Kinetics Human Action Video Dataset.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition The Kinetics Human Action Video Dataset

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T22:27:40.122220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1194cf6b-2017-4347-9730-afaeed236a1f · outbound

This paper cites Benchmarking micro-action recognition: Dataset, methods, and applications,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Benchmarking micro-action recognition: Dataset, methods, and applications,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.934657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4b4263b8-20be-4149-8965-c717202842b3 · outbound

This paper cites Quo vadis, action recognition? a new model and the kinetics dataset,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Quo vadis, action recognition? a new model and the kinetics dataset,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.922436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 62e2f2dc-7870-41a3-9d90-46fc76f28263 · outbound

This paper cites Slowfast networks for video recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Slowfast networks for video recognition,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.911990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 26ea1807-0044-45b1-ba10-5c8df18bb87c · outbound

This paper cites Spatio- temporal adaptive network with bidirectional temporal difference for action recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Spatio- temporal adaptive network with bidirectional temporal difference for action recognition,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.901766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation cc2b007b-c9da-4e9b-8851-659392ae8da2 · outbound

This paper cites Agpn: Action granu- larity pyramid network for video action recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Agpn: Action granu- larity pyramid network for video action recognition,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.892327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8fd14a40-fad8-4ce5-9bab-b86567274927 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T22:27:40.148881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8798e85-d7cd-470b-bb11-a27c9dec6e2c · outbound

This paper cites Is space-time attention all you need for video understanding?,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Is space-time attention all you need for video understanding?,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.882379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ce33abab-ab98-4780-a598-eb9d8d758f4d · outbound

This paper cites Video trans- former network,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Video trans- former network,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.872162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3044da5a-160d-4259-a067-821e792a9988 · outbound

This paper cites Video swin transformer,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Video swin transformer,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.861137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b0bc3023-a163-4fef-a986-30e193666464 · outbound

This paper cites Uniformer: Unifying convolution and self-attention for visual recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Uniformer: Unifying convolution and self-attention for visual recognition,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.849775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3960f5b7-2ff6-40aa-9cf1-c12ea214b332 · outbound

This paper cites Token shift transformer for video classification,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Token shift transformer for video classification,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.838731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 463272fb-7394-4e9a-9dfe-22b32e2c2ab8 · outbound

This paper cites Long-term leap attention, short-term periodic shift for video classification,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Long-term leap attention, short-term periodic shift for video classification,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.827829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1414484c-054b-4516-a2f6-83214a961ae3 · outbound

This paper cites Temporal shift module-based vision transformer network for action recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Temporal shift module-based vision transformer network for action recognition,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.817466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 04d9fdcb-6eab-4b31-a445-aeea2fb72618 · outbound

This paper cites Tsm: Temporal shift module for efficient and scalable video understanding on edge devices,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Tsm: Temporal shift module for efficient and scalable video understanding on edge devices,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.807475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0bf1222e-5649-486f-96a1-aa4919480ef8 · outbound

This paper cites Deep residual learning for image recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Deep residual learning for image recognition,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.796691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 772b8dea-c713-446b-9342-447d31407942 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Swin transformer: Hierarchical vision transformer using shifted windows,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.785994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6ad807c0-1c73-4d7f-9606-7e8fdd14d417 · outbound

This paper cites Movinets: Mobile video networks for efficient video ACCEPTED ON IEEE INTERNET OF THINGS JOURNAL 15 recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Movinets: Mobile video networks for efficient video ACCEPTED ON IEEE INTERNET OF THINGS JOURNAL 15 recognition,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.775546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9d08b420-9f98-4c2b-b032-70a8f1cb964e · outbound

This paper cites Deepsensemoe: Harnessing power of time series foundation models for few-shot human activity recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Deepsensemoe: Harnessing power of time series foundation models for few-shot human activity recognition,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.764881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6c045643-67e1-4125-b284-596da58b7944 · outbound

This paper cites Sensor- prompt tuning: Aligning time series foundational models with motion sensors for few-shot activity recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Sensor- prompt tuning: Aligning time series foundational models with motion sensors for few-shot activity recognition,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.754344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5bc425de-23e7-4ef0-8155-74d804e89a77 · outbound

This paper cites Deep convolutional state space model as human activity recognizer,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Deep convolutional state space model as human activity recognizer,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.743235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b542c21c-f478-417e-8558-f9abb5e7654c · outbound

This paper cites Learn- ing spatiotemporal features with 3d convolutional networks,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Learn- ing spatiotemporal features with 3d convolutional networks,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.732960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c064a65e-95c7-4a90-bfcd-e2333808ac90 · outbound

This paper cites A closer look at spatiotemporal convolutions for action recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition A closer look at spatiotemporal convolutions for action recognition,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.722844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 889b1fdd-02e0-4eff-96ba-2b1ae6d532b6 · outbound

This paper cites Tsm: Temporal shift module for efficient video understanding,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Tsm: Temporal shift module for efficient video understanding,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.712154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3d071749-dd3b-42a2-9c07-3981aa196216 · outbound

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

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition X3d: Expanding architectures for efficient video recognition,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.701981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 729c1e57-65a2-4d73-81cb-26df37db1c56 · outbound

This paper cites Mtrfn: Multiscale temporal receptive field network for compressed video action recognition at edge servers,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Mtrfn: Multiscale temporal receptive field network for compressed video action recognition at edge servers,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.691571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5b77e6e9-d2db-4631-b17f-7e60f9a968b0 · outbound

This paper cites Temporal transformer networks with self-supervision for action recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Temporal transformer networks with self-supervision for action recognition,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.681114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 95c756aa-a568-4c49-a90c-ce7b5bfe3865 · outbound

This paper cites Pyramid vision transformer: A versatile backbone for dense prediction without convolutions,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Pyramid vision transformer: A versatile backbone for dense prediction without convolutions,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.670335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d1b090fb-e234-4404-a965-50a561d4c5b5 · outbound

This paper cites Pvt v2: Improved baselines with pyramid vision transformer,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Pvt v2: Improved baselines with pyramid vision transformer,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.658243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ccbfb6c9-0cfc-4c6e-9830-bf21875327dd · outbound

This paper cites Edgenext: efficiently amalgamated cnn-transformer architecture for mobile vision applications,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Edgenext: efficiently amalgamated cnn-transformer architecture for mobile vision applications,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.647566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1b78b9a3-814b-45ac-a18d-ab3b3aaca3e9 · outbound

This paper cites Fastvit: A fast hybrid vision transformer using structural reparameteriza- tion,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Fastvit: A fast hybrid vision transformer using structural reparameteriza- tion,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.635765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 752c26c3-a8d0-481d-9f8c-6dfbf5cc5ae8 · outbound

This paper cites Effi- cientvit: Memory efficient vision transformer with cascaded group attention,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Effi- cientvit: Memory efficient vision transformer with cascaded group attention,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.624674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4beaa791-5f24-4b2b-8c86-5158c16d44cc · outbound

This paper cites Rethinking vision transformers for mobilenet size and speed,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Rethinking vision transformers for mobilenet size and speed,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.614803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b5c99eb8-664c-4ef5-8860-264cf1970b49 · outbound

This paper cites Shvit: Single-head vision transformer with memory efficient macro design,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Shvit: Single-head vision transformer with memory efficient macro design,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.604805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 04aa0bbd-f7bf-4c89-8bda-e918efc119aa · outbound

This paper cites S2aformer: Strip self-attention for efficient vision transformer,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition S2aformer: Strip self-attention for efficient vision transformer,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.595095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation aef23658-fa46-492f-a303-37dfa7c8481c · outbound

This paper cites Training data-efficient image transformers & distilla- tion through attention,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Training data-efficient image transformers & distilla- tion through attention,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.585278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c4753d23-db85-4daa-bd20-490a226cb9ad · outbound

This paper cites Tlee: Temporal-wise and layer-wise early exiting network for efficient video recognition on edge devices,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Tlee: Temporal-wise and layer-wise early exiting network for efficient video recognition on edge devices,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.574896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b7eacfc3-ca65-47d7-929c-9ac7e9abf9cd · outbound

This paper cites Conditional positional encodings for vision transformers,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Conditional positional encodings for vision transformers,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.564719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c5b0fe72-9df0-48ea-8447-996c99abc3e7 · outbound

This paper cites Imagenet large scale visual recognition challenge,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Imagenet large scale visual recognition challenge,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.554668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a0359cc6-4548-4b47-93ec-df57e8c33dbc · outbound

This paper cites Iformer: Integrating convnet and transformer for mo- bile application,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Iformer: Integrating convnet and transformer for mo- bile application,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.543574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 478bf45f-a4b1-4e34-9118-af9a6d1f8e93 · outbound

This paper cites Microvit: a vision transformer with low complexity self attention for edge device,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Microvit: a vision transformer with low complexity self attention for edge device,

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.533254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 51d46b3f-33ab-4ba9-a11d-3fb252a9bef7 · outbound

This paper cites Large Batch Optimization for Deep Learning: Training BERT in 76 minutes.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Large Batch Optimization for Deep Learning: Training BERT in 76 minutes

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-10T22:27:40.305685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b731ffae-4e2c-4e47-ac7a-7fe3e1cf27cc · outbound

This paper cites Group contextualization for video recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Group contextualization for video recognition,

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.522633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e1eae3e9-f5ae-4e1d-99a6-98ad33e4bfc9 · outbound

This paper cites Learning spatiotem- poral and motion features in a unified 2d network for action recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Learning spatiotem- poral and motion features in a unified 2d network for action recognition,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.511593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2174d477-b034-4b21-8254-dd2b83a0c945 · outbound

This paper cites Multiscale vision transformers,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Multiscale vision transformers,

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.501117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3ca3896b-5bed-4a27-b671-2078122ca882 · outbound

This paper cites Dualactnet: Exploiting slowfast architecture for micro-action recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Dualactnet: Exploiting slowfast architecture for micro-action recognition,

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.489940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 93cdfa9f-f153-45ec-8485-cf68f92763a4 · outbound

This paper cites Tdn: Temporal difference networks for efficient action recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Tdn: Temporal difference networks for efficient action recognition,

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.477359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c8d05b21-cdd9-4aec-bba6-d7c78fb0df7c · outbound

This paper cites Mobile Video Action Recognition.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Mobile Video Action Recognition

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-08-10T22:27:40.378607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5cd6d466-e69a-4f01-aeca-31dfc4634eb3 · outbound

This paper cites Compressed video action recognition,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Compressed video action recognition,

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.466025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fbd6d38c-f0ea-419d-8702-989a200502b0 · outbound

This paper cites Afd- former: A hybrid transformer with asymmetric flow division for synthesized view quality enhancement,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Afd- former: A hybrid transformer with asymmetric flow division for synthesized view quality enhancement,

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.454538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4295a7c9-5fcc-4ede-af2d-9de71e111506 · outbound

This paper cites Token fusion: Bridging the gap between token pruning and token merging,.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition Token fusion: Bridging the gap between token pruning and token merging,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.442445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation cc0be8c5-e969-41e8-962b-04edaeae6b16 · outbound

This paper cites He is currently a Full Professor with the Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology.

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition He is currently a Full Professor with the Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology

Reference 2011

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:27:40.430469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers