{"list":"other","total":60,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2001.05566","title":"Image Segmentation Using Deep Learning: A Survey","created":"2020-01-15","cited_by_count":660},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"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":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"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":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"2312.02228","title":"PixelLM: Pixel Reasoning with Large Multimodal Model","created":"2023-12-04","cited_by_count":222},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"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":"2208.08984","title":"Open-Vocabulary Universal Image Segmentation with MaskCLIP","created":"2022-08-18","cited_by_count":132},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"1804.09626","title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","created":"2018-04-25","cited_by_count":128},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115},{"id":"2003.07758","title":"Multi-modal Dense Video Captioning","created":"2020-03-17","cited_by_count":113},{"id":"2308.07926","title":"CoDeF: Content Deformation Fields for Temporally Consistent Video Processing","created":"2023-08-15","cited_by_count":108},{"id":"2403.14598","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","created":"2024-03-21","cited_by_count":101},{"id":"1904.06807","title":"Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation","created":"2019-04-15","cited_by_count":97},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95},{"id":"2204.04752","title":"Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image","created":"2022-04-10","cited_by_count":88},{"id":"2007.00047","title":"A Survey on Instance Segmentation: State of the art","created":"2020-06-28","cited_by_count":85},{"id":"2401.10229","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","created":"2024-01-18","cited_by_count":75},{"id":"1703.07815","title":"Cross-View Image Matching for Geo-localization in Urban Environments","created":"2017-03-22","cited_by_count":69},{"id":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53},{"id":"2010.09982","title":"Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition","created":"2020-10-20","cited_by_count":50},{"id":"2308.01477","title":"HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions","created":"2023-08-02","cited_by_count":48},{"id":"2007.15781","title":"LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities","created":"2020-07-31","cited_by_count":47},{"id":"1807.01440","title":"Multi-task Mid-level Feature Alignment Network for Unsupervised Cross-Dataset Person Re-Identification","created":"2018-07-04","cited_by_count":34},{"id":"2410.10791","title":"CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic Perception of Driving Scenes","created":"2024-10-14","cited_by_count":33},{"id":"2203.04203","title":"AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant","created":"2022-03-08","cited_by_count":32},{"id":"2403.06351","title":"Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos","created":"2024-03-11","cited_by_count":32},{"id":"2308.07918","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","created":"2023-08-15","cited_by_count":31},{"id":"1808.05469","title":"Cross-view image synthesis using geometry-guided conditional GANs","created":"2018-08-14","cited_by_count":30},{"id":"2311.00180","title":"Object-centric Video Representation for Long-term Action Anticipation","created":"2023-10-31","cited_by_count":24},{"id":"2311.15841","title":"Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation","created":"2023-11-27","cited_by_count":24},{"id":"2408.14765","title":"CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesis","created":"2024-08-27","cited_by_count":23},{"id":"2110.10183","title":"Cascaded Cross MLP-Mixer GANs for Cross-View Image Translation","created":"2021-10-19","cited_by_count":21},{"id":"2405.17773","title":"XTrack: Multimodal Training Boosts RGB-X Video Object Trackers","created":"2024-05-28","cited_by_count":21},{"id":"2110.15904","title":"Learning Co-segmentation by Segment Swapping for Retrieval and Discovery","created":"2021-10-29","cited_by_count":15},{"id":"2403.09194","title":"Intention-driven Ego-to-Exo Video Generation","created":"2024-03-14","cited_by_count":13}],"next_cursor":null}