{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1912.08804","title":"SynSin: End-to-end View Synthesis from a Single Image","created":"2019-12-18","cited_by_count":364},{"id":"1702.05448","title":"Learning to Detect Human-Object Interactions","created":"2017-02-17","cited_by_count":240},{"id":"1406.2807","title":"The Secrets of Salient Object Segmentation","created":"2014-06-11","cited_by_count":200},{"id":"1604.03605","title":"What do different evaluation metrics tell us about saliency models?","created":"2016-04-12","cited_by_count":185},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"1709.07326","title":"AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection","created":"2017-09-21","cited_by_count":128},{"id":"2103.14862","title":"TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization","created":"2021-03-27","cited_by_count":123},{"id":"2202.10108","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","created":"2022-02-21","cited_by_count":117},{"id":"2011.08612","title":"Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things","created":"2020-11-17","cited_by_count":111},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"1804.09627","title":"Actor and Observer: Joint Modeling of First and Third-Person Videos","created":"2018-04-25","cited_by_count":103},{"id":"2103.16397","title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","created":"2021-03-30","cited_by_count":100},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99},{"id":"1904.11045","title":"Bridging the Domain Gap for Ground-to-Aerial Image Matching","created":"2019-04-24","cited_by_count":95},{"id":"1812.04777","title":"Extreme View Synthesis","created":"2018-12-12","cited_by_count":94},{"id":"2009.01439","title":"Learning Dexterous Grasping with Object-Centric Visual Affordances","created":"2020-09-03","cited_by_count":85},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82},{"id":"1604.03670","title":"Interactive Perception: Leveraging Action in Perception and Perception in Action","created":"2016-04-13","cited_by_count":78},{"id":"1803.09125","title":"Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition","created":"2018-03-24","cited_by_count":78},{"id":"2208.03826","title":"Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications","created":"2022-08-07","cited_by_count":78},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77},{"id":"1712.07576","title":"Learning to Act Properly: Predicting and Explaining Affordances from Images","created":"2017-12-20","cited_by_count":74},{"id":"2008.09241","title":"Learning Affordance Landscapes for Interaction Exploration in 3D Environments","created":"2020-08-21","cited_by_count":65},{"id":"2104.13454","title":"Estimating Egocentric 3D Human Pose in Global Space","created":"2021-04-27","cited_by_count":56},{"id":"1610.01563","title":"DeepGaze II: Reading fixations from deep features trained on object recognition","created":"2016-10-05","cited_by_count":55},{"id":"1609.01064","title":"A Deep Multi-Level Network for Saliency Prediction","created":"2016-09-05","cited_by_count":54},{"id":"2007.03380","title":"Re-thinking Co-Salient Object Detection","created":"2020-07-07","cited_by_count":54},{"id":"2103.04523","title":"Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization","created":"2021-03-08","cited_by_count":46},{"id":"2206.04042","title":"Learning Ego 3D Representation as Ray Tracing","created":"2022-06-08","cited_by_count":43},{"id":"2108.03658","title":"One-Shot Object Affordance Detection in the Wild","created":"2021-08-08","cited_by_count":40},{"id":"2004.13364","title":"Gradient-Induced Co-Saliency Detection","created":"2020-04-28","cited_by_count":39},{"id":"2008.01270","title":"Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation","created":"2020-08-04","cited_by_count":36},{"id":"2106.14747","title":"One-Shot Affordance Detection","created":"2021-06-28","cited_by_count":32},{"id":"2203.04203","title":"AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant","created":"2022-03-08","cited_by_count":32},{"id":"1912.10867","title":"Analysis of the hands in egocentric vision: A survey","created":"2019-12-23","cited_by_count":25},{"id":"2108.05675","title":"Learning Visual Affordance Grounding from Demonstration Videos","created":"2021-08-12","cited_by_count":25},{"id":"2112.00580","title":"Background Activation Suppression for Weakly Supervised Object Localization","created":"2021-12-01","cited_by_count":22},{"id":"1807.06775","title":"Visual Affordance and Function Understanding: A Survey","created":"2018-07-18","cited_by_count":20},{"id":"1906.05857","title":"Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation","created":"2019-06-13","cited_by_count":20},{"id":"2202.12076","title":"Phrase-Based Affordance Detection via Cyclic Bilateral Interaction","created":"2022-02-24","cited_by_count":19},{"id":"1704.06340","title":"Identifying First-person Camera Wearers in Third-person Videos","created":"2017-04-20","cited_by_count":18},{"id":"1707.02850","title":"Adaptive Binarization for Weakly Supervised Affordance Segmentation","created":"2017-07-10","cited_by_count":16},{"id":"1711.08922","title":"Summarizing First-Person Videos from Third Persons' Points of Views","created":"2017-11-24","cited_by_count":15},{"id":"1505.01085","title":"In Defense of the Direct Perception of Affordances","created":"2015-05-05","cited_by_count":9},{"id":"1605.02964","title":"Weakly Supervised Learning of Affordances","created":"2016-05-10","cited_by_count":1}],"next_cursor":null}