{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2011.07231","title":"ActBERT: Learning Global-Local Video-Text Representations","created":"2020-11-14","cited_by_count":267},{"id":"2412.03555","title":"PaliGemma 2: A Family of Versatile VLMs for Transfer","created":"2024-12-04","cited_by_count":207},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149},{"id":"1906.11415","title":"Few-Shot Video Classification via Temporal Alignment","created":"2019-06-27","cited_by_count":125},{"id":"2105.09996","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","created":"2021-05-20","cited_by_count":102},{"id":"1901.02598","title":"D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation","created":"2019-01-09","cited_by_count":83},{"id":"2108.02833","title":"Elaborative Rehearsal for Zero-shot Action Recognition","created":"2021-08-05","cited_by_count":77},{"id":"1607.08584","title":"Connectionist Temporal Modeling for Weakly Supervised Action Labeling","created":"2016-07-28","cited_by_count":70},{"id":"2401.02418","title":"Learning to Prompt with Text Only Supervision for Vision-Language Models","created":"2024-01-04","cited_by_count":38},{"id":"2308.03063","title":"M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition","created":"2023-08-06","cited_by_count":34},{"id":"2109.01305","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","created":"2021-09-03","cited_by_count":29},{"id":"2406.13327","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","created":"2024-06-19","cited_by_count":23},{"id":"1505.06027","title":"Weakly-Supervised Alignment of Video With Text","created":"2015-05-22","cited_by_count":21},{"id":"2410.05774","title":"ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition","created":"2024-10-08","cited_by_count":21},{"id":"2312.08010","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","created":"2023-12-13","cited_by_count":14},{"id":"2408.06158","title":"OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning","created":"2024-08-12","cited_by_count":14},{"id":"1803.00057","title":"A Neural Multi-sequence Alignment TeCHnique (NeuMATCH)","created":"2018-02-19","cited_by_count":13},{"id":"2404.09490","title":"Leveraging Temporal Contextualization for Video Action Recognition","created":"2024-04-15","cited_by_count":9},{"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},{"id":"2207.11805","title":"Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions","created":"2022-07-24","cited_by_count":8},{"id":"2108.06647","title":"Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning","created":"2021-08-15","cited_by_count":7},{"id":"2408.16412","title":"Text-Enhanced Zero-Shot Action Recognition: A training-free approach","created":"2024-08-29","cited_by_count":6},{"id":"2408.16729","title":"Prediction-Feedback DETR for Temporal Action Detection","created":"2024-08-29","cited_by_count":5},{"id":"2412.21205","title":"Action-Agnostic Point-Level Supervision for Temporal Action Detection","created":"2024-12-30","cited_by_count":5},{"id":"2208.01897","title":"Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition","created":"2022-08-03","cited_by_count":4},{"id":"2409.01448","title":"FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition","created":"2024-09-02","cited_by_count":3}],"next_cursor":null}