{"list":"other","total":63,"rows":[{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"1709.05424","title":"NIMA: Neural Image Assessment","created":"2017-09-15","cited_by_count":389},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337},{"id":"2211.04894","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","created":"2022-11-09","cited_by_count":320},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"1905.00953","title":"Omni-Scale Feature Learning for Person Re-Identification","created":"2019-05-02","cited_by_count":295},{"id":"1710.10467","title":"Generalized End-to-End Loss for Speaker Verification","created":"2017-10-28","cited_by_count":293},{"id":"2010.15258","title":"DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors","created":"2020-10-28","cited_by_count":241},{"id":"2308.03060","title":"TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment","created":"2023-08-06","cited_by_count":226},{"id":"2503.06800","title":"VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation","created":"2025-03-09","cited_by_count":149},{"id":"2404.01292","title":"Measuring Style Similarity in Diffusion Models","created":"2024-04-01","cited_by_count":109},{"id":"2505.20292","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","created":"2025-05-26","cited_by_count":73},{"id":"2504.04907","title":"Video-Bench: Human-Aligned Video Generation Benchmark","created":"2025-04-07","cited_by_count":57},{"id":"2606.03748","title":"Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models","created":"2026-06-02","cited_by_count":57},{"id":"2510.20822","title":"HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives","created":"2025-10-23","cited_by_count":54},{"id":"2507.14533","title":"ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding","created":"2025-07-19","cited_by_count":41},{"id":"2512.19539","title":"StoryMem: Multi-shot Long Video Storytelling with Memory","created":"2025-12-22","cited_by_count":40},{"id":"2408.09787","title":"Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation","created":"2024-08-19","cited_by_count":37},{"id":"2411.15262","title":"MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation","created":"2024-11-22","cited_by_count":36},{"id":"2601.03655","title":"VideoMemory: Toward Consistent Video Generation via Memory Integration","created":"2026-01-07","cited_by_count":25},{"id":"2503.23452","title":"VideoGen-Eval: Agent-based System for Video Generation Evaluation","created":"2025-03-30","cited_by_count":23},{"id":"2506.21356","title":"ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models","created":"2025-06-26","cited_by_count":22},{"id":"2507.11245","title":"NarrLV: Towards a Comprehensive Narrative-Centric Evaluation for Long Video Generation","created":"2025-07-15","cited_by_count":22},{"id":"2512.21675","title":"UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture","created":"2025-12-25","cited_by_count":22},{"id":"2605.28091","title":"Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation","created":"2026-05-27","cited_by_count":22},{"id":"2508.08487","title":"MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling","created":"2025-08-11","cited_by_count":21},{"id":"2506.10540","title":"AniMaker: Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation","created":"2025-06-12","cited_by_count":19},{"id":"2606.00793","title":"MBench: A Comprehensive Benchmark on Memory Capability for Video World Models","created":"2026-05-30","cited_by_count":18},{"id":"2511.08521","title":"UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist","created":"2025-11-11","cited_by_count":15},{"id":"2602.23969","title":"MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation","created":"2026-02-27","cited_by_count":12},{"id":"2606.07649","title":"ViMax: Agentic Video Generation","created":"2026-06-02","cited_by_count":12},{"id":"2605.12496","title":"CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives","created":"2026-05-12","cited_by_count":10},{"id":"2604.23789","title":"MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation","created":"2026-04-26","cited_by_count":9},{"id":"2605.16003","title":"Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation","created":"2026-05-15","cited_by_count":9},{"id":"2605.26244","title":"LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV","created":"2026-05-25","cited_by_count":9},{"id":"2510.26412","title":"LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation","created":"2025-10-30","cited_by_count":7},{"id":"2606.08091","title":"VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation","created":"2026-06-06","cited_by_count":7},{"id":"2512.10286","title":"ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions","created":"2025-12-11","cited_by_count":6},{"id":"2605.06924","title":"A$^2$RD: Agentic Autoregressive Diffusion for Long Video Consistency","created":"2026-05-07","cited_by_count":6},{"id":"2605.15199","title":"EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation","created":"2026-05-14","cited_by_count":6},{"id":"2605.22144","title":"One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems","created":"2026-05-21","cited_by_count":6},{"id":"2605.26525","title":"ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation","created":"2026-05-26","cited_by_count":6},{"id":"2606.09639","title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","created":"2026-06-08","cited_by_count":6},{"id":"2606.21661","title":"UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating","created":"2026-06-19","cited_by_count":6},{"id":"2607.14189","title":"MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation","created":"2026-07-15","cited_by_count":6},{"id":"2605.17423","title":"Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration","created":"2026-05-17","cited_by_count":5},{"id":"2605.23271","title":"EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation","created":"2026-05-22","cited_by_count":5},{"id":"2511.18825","title":"Q-Save: Towards Scoring and Attribution for Generated Video Evaluation","created":"2025-11-24","cited_by_count":4},{"id":"2605.28035","title":"MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation","created":"2026-05-27","cited_by_count":4},{"id":"2605.30090","title":"DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent Evaluation","created":"2026-05-28","cited_by_count":4},{"id":"2602.01623","title":"Omni-Judge: Can Omni-LLMs Serve as Human-Aligned Judges for Text-Conditioned Audio-Video Generation?","created":"2026-02-02","cited_by_count":3},{"id":"2605.23610","title":"EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation","created":"2026-05-22","cited_by_count":3},{"id":"2607.24241","title":"FilmBench: A Film-Grade Benchmark for Cinematic Video Generation","created":"2026-07-27","cited_by_count":3},{"id":"2512.19012","title":"DramaBench: A Six-Dimensional Evaluation Framework for Drama Script Continuation","created":"2025-12-22","cited_by_count":2},{"id":"2605.27891","title":"SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control","created":"2026-05-27","cited_by_count":2},{"id":"2606.24107","title":"DramaDirector: Geometry-Guided Short Drama Generation","created":"2026-06-23","cited_by_count":2},{"id":"2607.13527","title":"VGIF-Score: Interpretable and Diagnostic Evaluation of Spatio-Temporal Instruction Following in Video Generation","created":"2026-07-15","cited_by_count":1}],"next_cursor":null}