{"list":"other","total":146,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1607.00653","title":"node2vec: Scalable Feature Learning for Networks","created":"2016-07-03","cited_by_count":1918},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2012.00451","title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos","created":"2020-12-01","cited_by_count":248},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225},{"id":"2408.16725","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","created":"2024-08-29","cited_by_count":210},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"2501.01957","title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","created":"2025-01-03","cited_by_count":197},{"id":"2408.05211","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","created":"2024-08-09","cited_by_count":173},{"id":"2406.08085","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","created":"2024-06-12","cited_by_count":169},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167},{"id":"2309.17024","title":"HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World","created":"2023-09-29","cited_by_count":166},{"id":"2411.03628","title":"StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding","created":"2024-11-06","cited_by_count":144},{"id":"2501.05510","title":"OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?","created":"2025-01-09","cited_by_count":142},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"2501.03218","title":"Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction","created":"2025-01-06","cited_by_count":127},{"id":"1506.09215","title":"Unsupervised Learning from Narrated Instruction Videos","created":"2015-06-30","cited_by_count":116},{"id":"2410.11190","title":"Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities","created":"2024-10-15","cited_by_count":109},{"id":"2206.03001","title":"PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System","created":"2022-06-07","cited_by_count":106},{"id":"2308.11339","title":"ProAgent: Building Proactive Cooperative Agents with Large Language Models","created":"2023-08-22","cited_by_count":98},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91},{"id":"2410.12361","title":"Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance","created":"2024-10-16","cited_by_count":87},{"id":"2201.10990","title":"Learning To Recognize Procedural Activities with Distant Supervision","created":"2022-01-26","cited_by_count":85},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84},{"id":"2106.11149","title":"OadTR: Online Action Detection with Transformers","created":"2021-06-21","cited_by_count":83},{"id":"1911.11206","title":"Oops! Predicting Unintentional Action in Video","created":"2019-11-25","cited_by_count":82},{"id":"2207.10883","title":"My View is the Best View: Procedure Learning from Egocentric Videos","created":"2022-07-22","cited_by_count":81},{"id":"2307.16368","title":"AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?","created":"2023-07-31","cited_by_count":81},{"id":"1904.04189","title":"Unsupervised learning of action classes with continuous temporal embedding","created":"2019-04-08","cited_by_count":76},{"id":"2501.13468","title":"Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge","created":"2025-01-23","cited_by_count":73},{"id":"1604.06506","title":"Online Action Detection","created":"2016-04-21","cited_by_count":69},{"id":"1805.06875","title":"NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning","created":"2018-05-17","cited_by_count":67},{"id":"2305.02750","title":"A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects","created":"2023-05-04","cited_by_count":66},{"id":"2506.09344","title":"Ming-Omni: A Unified Multimodal Model for Perception and Generation","created":"2025-06-11","cited_by_count":66},{"id":"2312.06505","title":"Grounded Question-Answering in Long Egocentric Videos","created":"2023-12-11","cited_by_count":64},{"id":"2505.05467","title":"StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant","created":"2025-05-08","cited_by_count":63},{"id":"2209.09236","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","created":"2022-09-19","cited_by_count":58},{"id":"2502.10810","title":"SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding","created":"2025-02-15","cited_by_count":57},{"id":"2408.16730","title":"VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation","created":"2024-08-29","cited_by_count":55},{"id":"2312.10300","title":"Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos","created":"2023-12-16","cited_by_count":54},{"id":"2208.04464","title":"In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation","created":"2022-08-08","cited_by_count":51},{"id":"2312.03391","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","created":"2023-12-06","cited_by_count":51},{"id":"2312.05269","title":"LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos","created":"2023-12-07","cited_by_count":51},{"id":"2312.14556","title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","created":"2023-12-22","cited_by_count":51},{"id":"2211.09529","title":"InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges","created":"2022-11-17","cited_by_count":48},{"id":"2310.17323","title":"IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting","created":"2023-10-26","cited_by_count":48},{"id":"2412.09596","title":"InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions","created":"2024-12-12","cited_by_count":48},{"id":"2411.17991","title":"VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format","created":"2024-11-27","cited_by_count":47},{"id":"2301.00746","title":"NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory","created":"2023-01-02","cited_by_count":46},{"id":"2408.14469","title":"Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos","created":"2024-08-26","cited_by_count":45},{"id":"2406.18070","title":"EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation","created":"2024-06-26","cited_by_count":44},{"id":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44},{"id":"1612.07796","title":"First-Person Activity Forecasting with Online Inverse Reinforcement Learning","created":"2016-12-22","cited_by_count":40},{"id":"2404.01933","title":"PREGO: online mistake detection in PRocedural EGOcentric videos","created":"2024-04-02","cited_by_count":39},{"id":"2106.09645","title":"Prototypical Graph Contrastive Learning","created":"2021-06-17","cited_by_count":37},{"id":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36},{"id":"2509.02722","title":"Planning with Reasoning using Vision Language World Model","created":"2025-09-02","cited_by_count":36},{"id":"1912.08077","title":"Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition","created":"2019-12-15","cited_by_count":35},{"id":"2203.04203","title":"AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant","created":"2022-03-08","cited_by_count":32},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29},{"id":"2312.03849","title":"LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning","created":"2023-12-06","cited_by_count":28}],"next_cursor":"100"}