{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"1812.11703","title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","created":"2018-12-31","cited_by_count":446},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350},{"id":"1904.07220","title":"Learning Discriminative Model Prediction for Tracking","created":"2019-04-15","cited_by_count":344},{"id":"1803.10794","title":"TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild","created":"2018-03-28","cited_by_count":343},{"id":"2203.11991","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","created":"2022-03-22","cited_by_count":330},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1811.07628","title":"ATOM: Accurate Tracking by Overlap Maximization","created":"2018-11-19","cited_by_count":285},{"id":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"2212.05034","title":"SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model","created":"2022-12-09","cited_by_count":278},{"id":"1611.09224","title":"ECO: Efficient Convolution Operators for Tracking","created":"2016-11-28","cited_by_count":239},{"id":"1809.00461","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","created":"2018-09-03","cited_by_count":232},{"id":"2003.12565","title":"Probabilistic Regression for Visual Tracking","created":"2020-03-27","cited_by_count":231},{"id":"2108.05699","title":"Oriented R-CNN for Object Detection","created":"2021-08-12","cited_by_count":231},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225},{"id":"1808.06048","title":"Distractor-aware Siamese Networks for Visual Object Tracking","created":"2018-08-18","cited_by_count":187},{"id":"2112.00995","title":"SwinTrack: A Simple and Strong Baseline for Transformer Tracking","created":"2021-12-02","cited_by_count":126},{"id":"2003.13045","title":"Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation","created":"2020-03-29","cited_by_count":120},{"id":"2203.11192","title":"Transforming Model Prediction for Tracking","created":"2022-03-21","cited_by_count":117},{"id":"2211.16940","title":"DiffPose: Toward More Reliable 3D Pose Estimation","created":"2022-11-30","cited_by_count":100},{"id":"2004.06711","title":"Deformable Siamese Attention Networks for Visual Object Tracking","created":"2020-04-14","cited_by_count":97},{"id":"2103.15538","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","created":"2021-03-29","cited_by_count":84},{"id":"1904.01828","title":"Unsupervised Deep Tracking","created":"2019-04-03","cited_by_count":74},{"id":"2203.07363","title":"Implicit Motion Handling for Video Camouflaged Object Detection","created":"2022-03-14","cited_by_count":60},{"id":"2203.11191","title":"Robust Visual Tracking by Segmentation","created":"2022-03-21","cited_by_count":38},{"id":"2309.03179","title":"SLiMe: Segment Like Me","created":"2023-09-06","cited_by_count":34},{"id":"2403.05854","title":"LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content","created":"2024-03-09","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":"2007.11984","title":"Unsupervised Deep Representation Learning for Real-Time Tracking","created":"2020-07-22","cited_by_count":29},{"id":"2308.13369","title":"Distribution-Aligned Diffusion for Human Mesh Recovery","created":"2023-08-25","cited_by_count":27},{"id":"2108.12711","title":"Learning to Track Objects from Unlabeled Videos","created":"2021-08-28","cited_by_count":21},{"id":"2308.13893","title":"Unsupervised Domain Adaptation via Domain-Adaptive Diffusion","created":"2023-08-26","cited_by_count":20},{"id":"2304.04415","title":"Meta Compositional Referring Expression Segmentation","created":"2023-04-10","cited_by_count":18},{"id":"2204.01475","title":"Unsupervised Learning of Accurate Siamese Tracking","created":"2022-04-04","cited_by_count":16},{"id":"2205.03650","title":"Distilling Inter-Class Distance for Semantic Segmentation","created":"2022-05-07","cited_by_count":16},{"id":"2304.12043","title":"MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer","created":"2023-04-24","cited_by_count":15},{"id":"2407.00115","title":"Instance Temperature Knowledge Distillation","created":"2024-06-27","cited_by_count":3}],"next_cursor":null}