{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"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":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"1606.06650","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","created":"2016-06-21","cited_by_count":1476},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"1605.09673","title":"Dynamic Filter Networks","created":"2016-05-31","cited_by_count":319},{"id":"2212.13345","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","created":"2022-12-27","cited_by_count":266},{"id":"2012.05208","title":"On the Binding Problem in Artificial Neural Networks","created":"2020-12-09","cited_by_count":233},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154},{"id":"2102.12627","title":"How to represent part-whole hierarchies in a neural network","created":"2021-02-25","cited_by_count":123},{"id":"2107.07905","title":"Unsupervised Discovery of Object Radiance Fields","created":"2021-07-16","cited_by_count":101},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97},{"id":"2208.02245","title":"MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training","created":"2022-08-03","cited_by_count":94},{"id":"1705.01861","title":"Action Tubelet Detector for Spatio-Temporal Action Localization","created":"2017-05-04","cited_by_count":77},{"id":"2002.12915","title":"The Implicit and Explicit Regularization Effects of Dropout","created":"2020-02-28","cited_by_count":71},{"id":"1911.06644","title":"You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization","created":"2019-11-15","cited_by_count":59},{"id":"2001.04608","title":"Actions as Moving Points","created":"2020-01-14","cited_by_count":55},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55},{"id":"2204.08412","title":"Temporally Efficient Vision Transformer for Video Instance Segmentation","created":"2022-04-18","cited_by_count":55},{"id":"1904.09288","title":"STEP: Spatio-Temporal Progressive Learning for Video Action Detection","created":"2019-04-19","cited_by_count":51},{"id":"2003.04490","title":"Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion","created":"2020-03-10","cited_by_count":47},{"id":"2212.11696","title":"Reversible Column Networks","created":"2022-12-22","cited_by_count":32},{"id":"1805.08162","title":"VideoCapsuleNet: A Simplified Network for Action Detection","created":"2018-05-21","cited_by_count":30},{"id":"1909.09300","title":"Making the Invisible Visible: Action Recognition Through Walls and Occlusions","created":"2019-09-20","cited_by_count":25},{"id":"2303.15879","title":"STMixer: A One-Stage Sparse Action Detector","created":"2023-03-28","cited_by_count":22},{"id":"2210.10046","title":"A Tri-Layer Plugin to Improve Occluded Detection","created":"2022-10-18","cited_by_count":21},{"id":"2203.04251","title":"End-to-End Semi-Supervised Learning for Video Action Detection","created":"2022-03-08","cited_by_count":17},{"id":"2304.03282","title":"Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention","created":"2023-04-06","cited_by_count":12},{"id":"2004.11475","title":"Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security Videos","created":"2020-04-23","cited_by_count":11},{"id":"2203.03282","title":"Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks","created":"2022-03-07","cited_by_count":11},{"id":"2207.11103","title":"DeVIS: Making Deformable Transformers Work for Video Instance Segmentation","created":"2022-07-22","cited_by_count":6},{"id":"2107.09270","title":"Locality-aware Channel-wise Dropout for Occluded Face Recognition","created":"2021-07-20","cited_by_count":5},{"id":"1812.02619","title":"Tube-CNN: Modeling temporal evolution of appearance for object detection in video","created":"2018-12-06","cited_by_count":2}],"next_cursor":null}