{"list":"other","total":100,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"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":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"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":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"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":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719},{"id":"1710.03957","title":"DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset","created":"2017-10-11","cited_by_count":652},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"1708.03985","title":"AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild","created":"2017-08-14","cited_by_count":492},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1604.01696","title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","created":"2016-04-06","cited_by_count":417},{"id":"1307.0414","title":"Challenges in Representation Learning: A report on three machine learning contests","created":"2013-07-01","cited_by_count":302},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200},{"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":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195},{"id":"2406.08085","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","created":"2024-06-12","cited_by_count":169},{"id":"1711.01731","title":"A Survey on Dialogue Systems: Recent Advances and New Frontiers","created":"2017-11-06","cited_by_count":162},{"id":"2312.00784","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","created":"2023-12-01","cited_by_count":161},{"id":"2501.06186","title":"LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs","created":"2025-01-10","cited_by_count":147},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146},{"id":"2406.11161","title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","created":"2024-06-17","cited_by_count":121},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113},{"id":"2403.18406","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","created":"2024-03-27","cited_by_count":97},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91},{"id":"2106.11149","title":"OadTR: Online Action Detection with Transformers","created":"2021-06-21","cited_by_count":83},{"id":"1805.06939","title":"Event2Mind: Commonsense Inference on Events, Intents, and Reactions","created":"2018-05-17","cited_by_count":82},{"id":"2306.04356","title":"Fine-Grained Visual Prompting","created":"2023-06-07","cited_by_count":82},{"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":"1802.08379","title":"EmotionLines: An Emotion Corpus of Multi-Party Conversations","created":"2018-02-23","cited_by_count":80},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80},{"id":"2003.02501","title":"Detecting Attended Visual Targets in Video","created":"2020-03-05","cited_by_count":77},{"id":"1604.06506","title":"Online Action Detection","created":"2016-04-21","cited_by_count":69},{"id":"2204.06806","title":"YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss","created":"2022-04-14","cited_by_count":68},{"id":"1712.06761","title":"MovieGraphs: Towards Understanding Human-Centric Situations from Videos","created":"2017-12-19","cited_by_count":67},{"id":"2107.00285","title":"iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis","created":"2021-07-01","cited_by_count":63},{"id":"1805.06533","title":"Modeling Naive Psychology of Characters in Simple Commonsense Stories","created":"2018-05-16","cited_by_count":60},{"id":"2209.09236","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","created":"2022-09-19","cited_by_count":58},{"id":"2409.15310","title":"Visual Prompting in Multimodal Large Language Models: A Survey","created":"2024-09-05","cited_by_count":54},{"id":"1609.06426","title":"From Facial Expression Recognition to Interpersonal Relation Prediction","created":"2016-09-21","cited_by_count":53},{"id":"2201.12728","title":"Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms","created":"2022-01-30","cited_by_count":51},{"id":"1906.04158","title":"Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in A Triadic Interaction","created":"2019-06-10","cited_by_count":48},{"id":"2204.08997","title":"A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets","created":"2022-04-19","cited_by_count":45},{"id":"2501.16566","title":"AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models","created":"2025-01-27","cited_by_count":44},{"id":"2206.08219","title":"HaGRID - HAnd Gesture Recognition Image Dataset","created":"2022-06-16","cited_by_count":43},{"id":"1909.01362","title":"Trouble on the Horizon: Forecasting the Derailment of Online Conversations as they Develop","created":"2019-09-03","cited_by_count":41},{"id":"1909.02144","title":"Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning","created":"2019-09-04","cited_by_count":40},{"id":"1907.02364","title":"Believe It or Not, We Know What You Are Looking at!","created":"2019-07-04","cited_by_count":38},{"id":"1611.00601","title":"Ordinal Common-sense Inference","created":"2016-11-02","cited_by_count":35},{"id":"2307.01630","title":"ChildPlay: A New Benchmark for Understanding Children's Gaze Behaviour","created":"2023-07-04","cited_by_count":35},{"id":"1906.05261","title":"LAEO-Net: revisiting people Looking At Each Other in videos","created":"2019-06-12","cited_by_count":34},{"id":"2410.11623","title":"VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI","created":"2024-10-15","cited_by_count":34},{"id":"2108.05479","title":"Automatic Gaze Analysis: A Survey of Deep Learning based Approaches","created":"2021-08-12","cited_by_count":33},{"id":"2407.21534","title":"ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models","created":"2024-07-31","cited_by_count":33},{"id":"2111.06647","title":"Speaker and Time-aware Joint Contextual Learning for Dialogue-act Classification in Counselling Conversations","created":"2021-11-12","cited_by_count":31},{"id":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28},{"id":"2409.18127","title":"EgoLM: Multi-Modal Language Model of Egocentric Motions","created":"2024-09-26","cited_by_count":28},{"id":"1506.06882","title":"SALSA: A Novel Dataset for Multimodal Group Behavior Analysis","created":"2015-06-23","cited_by_count":27},{"id":"2412.08646","title":"StreamChat: Chatting with Streaming Video","created":"2024-12-11","cited_by_count":24},{"id":"2412.03920","title":"A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios","created":"2024-12-05","cited_by_count":23},{"id":"2005.02134","title":"IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture Recognition","created":"2020-04-20","cited_by_count":22},{"id":"2404.11023","title":"Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions","created":"2024-04-17","cited_by_count":22},{"id":"2109.04919","title":"EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems","created":"2021-09-10","cited_by_count":20},{"id":"2303.16024","title":"Egocentric Auditory Attention Localization in Conversations","created":"2023-03-28","cited_by_count":18},{"id":"2403.02090","title":"Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations","created":"2024-03-04","cited_by_count":18},{"id":"2409.15316","title":"Towards Social AI: A Survey on Understanding Social Interactions","created":"2024-09-05","cited_by_count":16},{"id":"2501.06835","title":"X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding","created":"2025-01-12","cited_by_count":15},{"id":"2501.16643","title":"An LLM Benchmark for Addressee Recognition in Multi-modal Multi-party Dialogue","created":"2025-01-28","cited_by_count":15},{"id":"2210.13404","title":"Contrastive Representation Learning for Gaze Estimation","created":"2022-10-24","cited_by_count":14},{"id":"2410.21411","title":"SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization","created":"2024-10-28","cited_by_count":14},{"id":"2310.16301","title":"Is ChatGPT a Good Multi-Party Conversation Solver?","created":"2023-10-25","cited_by_count":13},{"id":"2205.11690","title":"Workflow Discovery from Dialogues in the Low Data Regime","created":"2022-05-24","cited_by_count":12},{"id":"2205.05177","title":"ConfLab: A Data Collection Concept, Dataset, and Benchmark for Machine Analysis of Free-Standing Social Interactions in the Wild","created":"2022-05-10","cited_by_count":10},{"id":"2312.01771","title":"IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks","created":"2023-12-04","cited_by_count":10},{"id":"1811.06937","title":"Mode Variational LSTM Robust to Unseen Modes of Variation: Application to Facial Expression Recognition","created":"2018-11-16","cited_by_count":7},{"id":"2311.05669","title":"Multi-Modal Gaze Following in Conversational Scenarios","created":"2023-11-09","cited_by_count":6},{"id":"2404.17205","title":"Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer","created":"2024-04-26","cited_by_count":5},{"id":"2410.14744","title":"Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors","created":"2024-10-17","cited_by_count":2},{"id":"2309.03877","title":"Introducing \"Forecast Utterance\" for Conversational Data Science","created":"2023-09-07","cited_by_count":1}],"next_cursor":null}