{"total":84,"rows":[{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310,"area":null},{"id":"2201.09450","title":"UniFormer: Unifying Convolution and Self-attention for Visual Recognition","created":"2022-01-24","cited_by_count":206,"area":null},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193,"area":null},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184,"area":null},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183,"area":null},{"id":"2111.12082","title":"PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer","created":"2021-11-23","cited_by_count":120,"area":null},{"id":"2205.03436","title":"EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers","created":"2022-05-06","cited_by_count":116,"area":null},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116,"area":null},{"id":"2207.07852","title":"TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval","created":"2022-07-16","cited_by_count":104,"area":null},{"id":"2212.04500","title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","created":"2022-12-08","cited_by_count":90,"area":"distill"},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2301.11116","title":"Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2302.00624","title":"Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization","created":"2023-02-01","cited_by_count":55,"area":null},{"id":"2211.09529","title":"InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges","created":"2022-11-17","cited_by_count":48,"area":null},{"id":"2302.03548","title":"PhysFormer++: Facial Video-based Physiological Measurement with SlowFast Temporal Difference Transformer","created":"2023-02-07","cited_by_count":48,"area":null},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41,"area":null},{"id":"2309.07911","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","created":"2023-09-14","cited_by_count":32,"area":null},{"id":"2307.07483","title":"Multimodal Distillation for Egocentric Action Recognition","created":"2023-07-14","cited_by_count":28,"area":"distill"},{"id":"2308.04549","title":"Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation","created":"2023-08-08","cited_by_count":24,"area":null},{"id":"2310.05010","title":"Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data","created":"2023-10-08","cited_by_count":22,"area":null},{"id":"2403.17935","title":"OmniVid: A Generative Framework for Universal Video Understanding","created":"2024-03-26","cited_by_count":22,"area":null},{"id":"2111.12527","title":"MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning","created":"2021-11-24","cited_by_count":21,"area":null},{"id":"2212.05638","title":"Cross-Modal Learning with 3D Deformable Attention for Action Recognition","created":"2022-12-12","cited_by_count":20,"area":null},{"id":"2304.08451","title":"Efficient Video Action Detection with Token Dropout and Context Refinement","created":"2023-04-17","cited_by_count":20,"area":null},{"id":"2211.06885","title":"SCOTCH and SODA: A Transformer Video Shadow Detection Framework","created":"2022-11-13","cited_by_count":19,"area":null},{"id":"2304.01110","title":"AutoLabel: CLIP-based framework for Open-set Video Domain Adaptation","created":"2023-04-03","cited_by_count":18,"area":null},{"id":"2309.01270","title":"COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers","created":"2023-09-03","cited_by_count":17,"area":"distill"},{"id":"2107.10771","title":"EAN: Event Adaptive Network for Enhanced Action Recognition","created":"2021-07-22","cited_by_count":16,"area":null},{"id":"2207.10448","title":"An Efficient Spatio-Temporal Pyramid Transformer for Action Detection","created":"2022-07-21","cited_by_count":16,"area":null},{"id":"2303.16268","title":"TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition","created":"2023-03-28","cited_by_count":16,"area":null},{"id":"2312.01897","title":"Adapting Short-Term Transformers for Action Detection in Untrimmed Videos","created":"2023-12-04","cited_by_count":16,"area":null},{"id":"2108.09635","title":"StarVQA: Space-Time Attention for Video Quality Assessment","created":"2021-08-22","cited_by_count":15,"area":null},{"id":"2207.13259","title":"Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition","created":"2022-07-27","cited_by_count":15,"area":null},{"id":"2211.10636","title":"EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens","created":"2022-11-19","cited_by_count":15,"area":null},{"id":"2305.03343","title":"LOGO-Former: Local-Global Spatio-Temporal Transformer for Dynamic Facial Expression Recognition","created":"2023-05-05","cited_by_count":15,"area":null},{"id":"2404.03924","title":"Learning Correlation Structures for Vision Transformers","created":"2024-04-05","cited_by_count":15,"area":null},{"id":"2203.03014","title":"Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos","created":"2022-03-06","cited_by_count":14,"area":null},{"id":"2305.15699","title":"Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2310.01324","title":"ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video","created":"2023-10-02","cited_by_count":14,"area":null},{"id":"2112.04674","title":"DualFormer: Local-Global Stratified Transformer for Efficient Video Recognition","created":"2021-12-09","cited_by_count":11,"area":null},{"id":"2207.09067","title":"Time Is MattEr: Temporal Self-supervision for Video Transformers","created":"2022-07-19","cited_by_count":11,"area":null},{"id":"2304.05292","title":"MC-ViViT: Multi-branch Classifier-ViViT to detect Mild Cognitive Impairment in older adults using facial videos","created":"2023-04-11","cited_by_count":11,"area":null},{"id":"2303.17228","title":"Streaming Video Model","created":"2023-03-30","cited_by_count":10,"area":null},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2412.09895","title":"Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP","created":"2024-12-13","cited_by_count":9,"area":null},{"id":"2204.04796","title":"SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition","created":"2022-04-10","cited_by_count":8,"area":null},{"id":"2401.10039","title":"GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition","created":"2024-01-18","cited_by_count":8,"area":"mllm"},{"id":"2308.05787","title":"Temporally-Adaptive Models for Efficient Video Understanding","created":"2023-08-10","cited_by_count":7,"area":null},{"id":"2411.13626","title":"Principles of Visual Tokens for Efficient Video Understanding","created":"2024-11-20","cited_by_count":7,"area":null},{"id":"2210.08164","title":"Linear Video Transformer with Feature Fixation","created":"2022-10-15","cited_by_count":6,"area":null},{"id":"2312.13746","title":"Video Recognition in Portrait Mode","created":"2023-12-21","cited_by_count":6,"area":null},{"id":"2204.00452","title":"Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition","created":"2022-04-01","cited_by_count":5,"area":null},{"id":"2311.06231","title":"Learning Human Action Recognition Representations Without Real Humans","created":"2023-11-10","cited_by_count":5,"area":null},{"id":"2506.14107","title":"D\\'ej\\`a Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2408.02421","title":"FE-Adapter: Adapting Image-based Emotion Classifiers to Videos","created":"2024-08-05","cited_by_count":4,"area":null},{"id":"2110.02902","title":"SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021","created":"2021-10-06","cited_by_count":3,"area":null},{"id":"2208.12257","title":"Video Mobile-Former: Video Recognition with Efficient Global Spatial-temporal Modeling","created":"2022-08-25","cited_by_count":3,"area":null},{"id":"2407.02934","title":"PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2506.20342","title":"Feature Hallucination for Self-supervised Action Recognition","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2112.08117","title":"Vision Transformer Based Video Hashing Retrieval for Tracing the Source of Fake Videos","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2112.10066","title":"LocFormer: Enabling Transformers to Perform Temporal Moment Localization on Long Untrimmed Videos With a Feature Sampling Approach","created":"2021-12-19","cited_by_count":2,"area":null},{"id":"2209.07474","title":"On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognition","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2304.02110","title":"DIR-AS: Decoupling Individual Identification and Temporal Reasoning for Action Segmentation","created":"2023-04-04","cited_by_count":2,"area":null},{"id":"2307.06527","title":"Free-Form Composition Networks for Egocentric Action Recognition","created":"2023-07-13","cited_by_count":2,"area":null},{"id":"2405.05584","title":"A Survey on Backbones for Deep Video Action Recognition","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2109.06474","title":"Space Time Recurrent Memory Network","created":"2021-09-14","cited_by_count":1,"area":null},{"id":"2208.11108","title":"Efficient Attention-free Video Shift Transformers","created":"2022-08-23","cited_by_count":1,"area":null},{"id":"2211.16289","title":"Lightweight Structure-Aware Attention for Visual Understanding","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2304.00325","title":"SVT: Supertoken Video Transformer for Efficient Video Understanding","created":"2023-04-01","cited_by_count":1,"area":null},{"id":"2304.05930","title":"MED-VT++: Unifying Multimodal Learning with a Multiscale Encoder-Decoder Video Transformer","created":"2023-04-12","cited_by_count":1,"area":null},{"id":"2308.12006","title":"Multi-stage Factorized Spatio-Temporal Representation for RGB-D Action and Gesture Recognition","created":"2023-08-23","cited_by_count":1,"area":null},{"id":"2605.06809","title":"LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2609.08505","title":"Temporal State Transport in Video Generation: Diagnosing and Correcting Spectral Imbalance","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2211.14449","title":"PatchBlender: A Motion Prior for Video Transformers","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2301.11880","title":"Optical Flow Estimation in 360$^\\circ$ Videos: Dataset, Model and Application","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2308.10533","title":"Joint learning of images and videos with a single Vision Transformer","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2401.07584","title":"Collaboratively Self-supervised Video Representation Learning for Action Recognition","created":"2024-01-15","cited_by_count":0,"area":null},{"id":"2402.18577","title":"Motion Guided Token Compression for Efficient Masked Video Modeling","created":"2024-01-10","cited_by_count":0,"area":"inference"},{"id":"2407.02123","title":"Hybrid Feature Collaborative Reconstruction Network for Few-Shot Fine-Grained Image Classification","created":"2024-07-02","cited_by_count":0,"area":null},{"id":"2504.08012","title":"SRVP: Strong Recollection Video Prediction Model Using Attention-Based Spatiotemporal Correlation Fusion","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2509.08228","title":"Sparse Transformer for Ultra-sparse Sampled Video Compressive Sensing","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2511.20928","title":"Smooth regularization for efficient video recognition","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2603.25977","title":"Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding (D-RoPE)","created":"2026-03-26","cited_by_count":0,"area":null}],"next_cursor":null}