{"total":36,"rows":[{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320,"area":null},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179,"area":null},{"id":"2304.03307","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","created":"2023-04-06","cited_by_count":91,"area":null},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83,"area":null},{"id":"2111.12374","title":"MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing","created":"2021-11-24","cited_by_count":39,"area":null},{"id":"2104.14135","title":"Action Unit Memory Network for Weakly Supervised Temporal Action Localization","created":"2021-04-29","cited_by_count":26,"area":null},{"id":"2210.16820","title":"Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition","created":"2022-10-30","cited_by_count":22,"area":null},{"id":"2106.15827","title":"When Video Classification Meets Incremental Classes","created":"2021-06-30","cited_by_count":18,"area":null},{"id":"2307.16813","title":"Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment","created":"2023-07-31","cited_by_count":18,"area":null},{"id":"2211.06742","title":"Deep Unsupervised Key Frame Extraction for Efficient Video Classification","created":"2022-11-12","cited_by_count":14,"area":null},{"id":"2312.08010","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","created":"2023-12-13","cited_by_count":14,"area":null},{"id":"2112.12668","title":"3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na\\\"ive","created":"2021-12-23","cited_by_count":10,"area":null},{"id":"2208.09424","title":"Hierarchical Compositional Representations for Few-shot Action Recognition","created":"2022-08-19","cited_by_count":10,"area":null},{"id":"2402.04599","title":"Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment","created":"2024-02-07","cited_by_count":10,"area":null},{"id":"2208.00394","title":"STrajNet: Multi-modal Hierarchical Transformer for Occupancy Flow Field Prediction in Autonomous Driving","created":"2022-07-31","cited_by_count":8,"area":null},{"id":"2307.10763","title":"Actor-agnostic Multi-label Action Recognition with Multi-modal Query","created":"2023-07-20","cited_by_count":8,"area":null},{"id":"2312.02226","title":"Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition","created":"2023-12-04","cited_by_count":8,"area":null},{"id":"2303.10451","title":"Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation","created":"2023-03-18","cited_by_count":7,"area":null},{"id":"2407.06162","title":"RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model","created":"2024-06-02","cited_by_count":5,"area":null},{"id":"2105.14740","title":"A Study On the Effects of Pre-processing On Spatio-temporal Action Recognition Using Spiking Neural Networks Trained with STDP","created":"2021-05-31","cited_by_count":4,"area":null},{"id":"2407.18289","title":"MARINE: A Computer Vision Model for Detecting Rare Predator-Prey Interactions in Animal Videos","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2205.15068","title":"Embedding Graphs on Grassmann Manifold","created":"2022-05-30","cited_by_count":2,"area":null},{"id":"2509.08908","title":"Diffusion-Based Action Recognition Generalizes to Untrained Domains","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2202.07402","title":"SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations","created":"2022-02-15","cited_by_count":1,"area":null},{"id":"2203.05156","title":"End-to-End Semantic Video Transformer for Zero-Shot Action Recognition","created":"2022-03-10","cited_by_count":1,"area":null},{"id":"2206.08632","title":"Learning Using Privileged Information for Zero-Shot Action Recognition","created":"2022-06-17","cited_by_count":1,"area":null},{"id":"2404.19383","title":"Cross-Block Fine-Grained Semantic Cascade for Skeleton-Based Sports Action Recognition","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2509.21783","title":"Prompt-guided Disentangled Representation for Action Recognition","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2112.10057","title":"Precondition and Effect Reasoning for Action Recognition","created":"2021-12-19","cited_by_count":0,"area":null},{"id":"2208.11885","title":"Visualizing the Passage of Time with Video Temporal Pyramids","created":"2022-08-25","cited_by_count":0,"area":null},{"id":"2209.05379","title":"Action-based Early Autism Diagnosis Using Contrastive Feature Learning","created":"2022-09-12","cited_by_count":0,"area":null},{"id":"2211.12748","title":"Dynamic Appearance: A Video Representation for Action Recognition with Joint Training","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2301.06082","title":"A Survey on Human Action Recognition","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2504.00794","title":"Conditional Temporal Neural Processes with Covariance Loss","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2507.20629","title":"DAMS:Dual-Branch Adaptive Multiscale Spatiotemporal Framework for Video Anomaly Detection","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2607.26097","title":"Knowledge-guided Disentanglement with Atomic Actions for Action Recognition","created":"2026-07-28","cited_by_count":0,"area":null}],"next_cursor":null}