{"list":"other","total":65,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2305.19118","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","created":"2023-05-30","cited_by_count":1011},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"2108.05565","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2021-08-12","cited_by_count":240},{"id":"2304.11968","title":"Track Anything: Segment Anything Meets Videos","created":"2023-04-24","cited_by_count":234},{"id":"2304.06790","title":"Inpaint Anything: Segment Anything Meets Image Inpainting","created":"2023-04-13","cited_by_count":233},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197},{"id":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"2310.12982","title":"Putting the Object Back into Video Object Segmentation","created":"2023-10-19","cited_by_count":188},{"id":"2312.00863","title":"EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything","created":"2023-12-01","cited_by_count":188},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"1803.08006","title":"Video Object Segmentation with Language Referring Expressions","created":"2018-03-21","cited_by_count":162},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161},{"id":"2207.05042","title":"Audio-Visual Segmentation","created":"2022-07-11","cited_by_count":151},{"id":"2210.09782","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","created":"2022-10-18","cited_by_count":148},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148},{"id":"2111.14821","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","created":"2021-11-29","cited_by_count":135},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124},{"id":"2301.13190","title":"Audio-Visual Segmentation with Semantics","created":"2023-01-30","cited_by_count":75},{"id":"2209.09634","title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","created":"2022-08-30","cited_by_count":73},{"id":"2307.01146","title":"AVSegFormer: Audio-Visual Segmentation with Transformer","created":"2023-07-03","cited_by_count":68},{"id":"2008.05789","title":"Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning","created":"2020-08-13","cited_by_count":63},{"id":"2307.09356","title":"OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation","created":"2023-07-18","cited_by_count":62},{"id":"2307.11545","title":"Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation","created":"2023-07-21","cited_by_count":61},{"id":"2310.03923","title":"Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation","created":"2023-10-05","cited_by_count":54},{"id":"2309.09709","title":"CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation","created":"2023-09-18","cited_by_count":53},{"id":"2207.01203","title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","created":"2022-07-04","cited_by_count":50},{"id":"2307.13537","title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","created":"2023-07-25","cited_by_count":48},{"id":"2305.11019","title":"Annotation-free Audio-Visual Segmentation","created":"2023-05-18","cited_by_count":46},{"id":"2109.04869","title":"PlaTe: Visually-Grounded Planning with Transformers in Procedural Tasks","created":"2021-09-10","cited_by_count":45},{"id":"2306.04121","title":"Matte Anything: Interactive Natural Image Matting with Segment Anything Models","created":"2023-06-07","cited_by_count":39},{"id":"2112.02853","title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","created":"2021-12-06","cited_by_count":36},{"id":"2309.03473","title":"Temporal Collection and Distribution for Referring Video Object Segmentation","created":"2023-09-07","cited_by_count":27},{"id":"2402.18115","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","created":"2024-02-28","cited_by_count":27},{"id":"2211.15103","title":"VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning","created":"2022-11-28","cited_by_count":25},{"id":"2312.15715","title":"UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces","created":"2023-12-25","cited_by_count":22},{"id":"2310.00132","title":"QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition","created":"2023-09-29","cited_by_count":20},{"id":"2206.12972","title":"VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning","created":"2022-06-26","cited_by_count":19},{"id":"2112.01695","title":"Hybrid Instance-aware Temporal Fusion for Online Video Instance Segmentation","created":"2021-12-03","cited_by_count":13},{"id":"2110.10599","title":"Video Instance Segmentation by Instance Flow Assembly","created":"2021-10-20","cited_by_count":12},{"id":"2207.00887","title":"Towards Robust Video Object Segmentation with Adaptive Object Calibration","created":"2022-07-02","cited_by_count":11},{"id":"2307.06924","title":"DRAGON: A Dialogue-Based Robot for Assistive Navigation with Visual Language Grounding","created":"2023-07-13","cited_by_count":9},{"id":"2402.08125","title":"Customizable Perturbation Synthesis for Robust SLAM Benchmarking","created":"2024-02-12","cited_by_count":6},{"id":"2012.08977","title":"Visually Grounding Language Instruction for History-Dependent Manipulation","created":"2020-12-16","cited_by_count":5},{"id":"2103.09720","title":"Few-Shot Visual Grounding for Natural Human-Robot Interaction","created":"2021-03-17","cited_by_count":2}],"next_cursor":null}