{"list":"other","total":69,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"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":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"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":"2001.05566","title":"Image Segmentation Using Deep Learning: A Survey","created":"2020-01-15","cited_by_count":660},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"2312.17090","title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","created":"2023-12-28","cited_by_count":503},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388},{"id":"2112.10764","title":"Mask2Former for Video Instance Segmentation","created":"2021-12-20","cited_by_count":171},{"id":"2311.06783","title":"Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models","created":"2023-11-12","cited_by_count":152},{"id":"2207.05042","title":"Audio-Visual Segmentation","created":"2022-07-11","cited_by_count":151},{"id":"2007.10558","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing","created":"2020-07-21","cited_by_count":146},{"id":"2501.11561","title":"Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution","created":"2025-01-20","cited_by_count":141},{"id":"2107.01153","title":"A Survey on Deep Learning Technique for Video Segmentation","created":"2021-07-02","cited_by_count":132},{"id":"2312.08962","title":"Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models","created":"2023-12-14","cited_by_count":105},{"id":"2503.22679","title":"Q-Insight: Understanding Image Quality via Visual Reinforcement Learning","created":"2025-03-28","cited_by_count":98},{"id":"2301.13190","title":"Audio-Visual Segmentation with Semantics","created":"2023-01-30","cited_by_count":75},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73},{"id":"1902.07473","title":"Dual-modality seq2seq network for audio-visual event localization","created":"2019-02-20","cited_by_count":72},{"id":"2104.00239","title":"Positive Sample Propagation along the Audio-Visual Event Line","created":"2021-04-01","cited_by_count":69},{"id":"2307.01146","title":"AVSegFormer: Audio-Visual Segmentation with Transformer","created":"2023-07-03","cited_by_count":68},{"id":"2309.09709","title":"CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation","created":"2023-09-18","cited_by_count":53},{"id":"2211.09980","title":"Contrastive Positive Sample Propagation along the Audio-Visual Event Line","created":"2022-11-18","cited_by_count":50},{"id":"2303.12930","title":"Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline","created":"2023-03-22","cited_by_count":46},{"id":"2409.20063","title":"Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMs","created":"2024-09-30","cited_by_count":39},{"id":"2310.08303","title":"Multimodal Variational Auto-encoder based Audio-Visual Segmentation","created":"2023-10-12","cited_by_count":38},{"id":"2404.14381","title":"TAVGBench: Benchmarking Text to Audible-Video Generation","created":"2024-04-22","cited_by_count":34},{"id":"2407.10957","title":"Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes","created":"2024-07-15","cited_by_count":33},{"id":"2204.11573","title":"Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing","created":"2022-04-25","cited_by_count":29},{"id":"2408.14008","title":"LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models","created":"2024-08-26","cited_by_count":28},{"id":"2412.19238","title":"FineVQ: Fine-Grained User Generated Content Video Quality Assessment","created":"2024-12-26","cited_by_count":28},{"id":"2411.11278","title":"Towards Open-Vocabulary Audio-Visual Event Localization","created":"2024-11-18","cited_by_count":26},{"id":"2407.08126","title":"Label-anticipated Event Disentanglement for Audio-Visual Video Parsing","created":"2024-07-11","cited_by_count":25},{"id":"2407.11820","title":"Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation","created":"2024-07-16","cited_by_count":23},{"id":"2508.00265","title":"Multimodal Referring Segmentation: A Survey","created":"2025-08-01","cited_by_count":22},{"id":"2510.24821","title":"Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation","created":"2025-10-28","cited_by_count":22},{"id":"2310.18709","title":"Audio-Visual Instance Segmentation","created":"2023-10-28","cited_by_count":21},{"id":"2406.00919","title":"Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling","created":"2024-06-03","cited_by_count":20},{"id":"2312.12816","title":"Object-aware Adaptive-Positivity Learning for Audio-Visual Question Answering","created":"2023-12-20","cited_by_count":19},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18},{"id":"2305.17343","title":"Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser","created":"2023-05-27","cited_by_count":18},{"id":"2503.13068","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","created":"2025-03-17","cited_by_count":18},{"id":"2506.01558","title":"SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes","created":"2025-06-02","cited_by_count":17},{"id":"2506.05384","title":"Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment","created":"2025-06-03","cited_by_count":14},{"id":"2412.10749","title":"Patch-level Sounding Object Tracking for Audio-Visual Question Answering","created":"2024-12-14","cited_by_count":13},{"id":"2412.11248","title":"Multimodal Class-aware Semantic Enhancement Network for Audio-Visual Video Parsing","created":"2024-12-15","cited_by_count":13},{"id":"2412.12628","title":"Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration","created":"2024-12-17","cited_by_count":12},{"id":"2507.22886","title":"Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation","created":"2025-07-30","cited_by_count":11},{"id":"2602.00607","title":"MTAVG-Bench: A Diagnostic Benchmark for Multi-Talker Dialogue-Centric Audio-Video Generation","created":"2026-01-31","cited_by_count":11},{"id":"2506.23271","title":"Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation","created":"2025-06-29","cited_by_count":10},{"id":"2508.06051","title":"VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning","created":"2025-08-08","cited_by_count":10},{"id":"2503.12840","title":"Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics","created":"2025-03-17","cited_by_count":9},{"id":"2508.04418","title":"Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation","created":"2025-08-06","cited_by_count":7},{"id":"2508.04566","title":"CLASP: Cross-modal Salient Anchor-based Semantic Propagation for Weakly-supervised Dense Audio-Visual Event Localization","created":"2025-08-06","cited_by_count":6},{"id":"2509.17537","title":"SimToken: A Simple Baseline for Referring Audio-Visual Segmentation","created":"2025-09-22","cited_by_count":6},{"id":"2512.16978","title":"A Benchmark for Omni-Modal Reasoning in Long Videos","created":"2025-12-18","cited_by_count":5},{"id":"2505.23155","title":"PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling","created":"2025-05-29","cited_by_count":4},{"id":"2506.11436","title":"TAViS: Text-bridged Audio-Visual Segmentation with Foundation Models","created":"2025-06-13","cited_by_count":4},{"id":"2509.22740","title":"Learning What To Hear: Boosting Sound-Source Association For Robust Audiovisual Instance Segmentation","created":"2025-09-26","cited_by_count":4},{"id":"2504.06884","title":"Audio-visual Event Localization on Portrait Mode Short Videos","created":"2025-04-09","cited_by_count":3},{"id":"2508.02149","title":"AURORA:Augmented Understanding via Structured Reasoning and Reinforcement Learning for Reference Audio-Visual Segmentation","created":"2025-08-04","cited_by_count":3},{"id":"2508.03724","title":"From Waveforms to Pixels: A Survey on Audio-Visual Segmentation","created":"2025-07-29","cited_by_count":3}],"next_cursor":null}