{"list":"other","total":65,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1812.11703","title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","created":"2018-12-31","cited_by_count":446},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1908.01998","title":"Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector","created":"2019-08-06","cited_by_count":206},{"id":"2003.06761","title":"Siamese Box Adaptive Network for Visual Tracking","created":"2020-03-15","cited_by_count":189},{"id":"2104.13682","title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","created":"2021-04-28","cited_by_count":183},{"id":"1904.11574","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","created":"2019-04-25","cited_by_count":154},{"id":"2111.14821","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","created":"2021-11-29","cited_by_count":135},{"id":"1710.03958","title":"Detect to Track and Track to Detect","created":"2017-10-11","cited_by_count":131},{"id":"1511.04164","title":"Natural Language Object Retrieval","created":"2015-11-13","cited_by_count":124},{"id":"2001.06891","title":"Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences","created":"2020-01-19","cited_by_count":118},{"id":"2109.00590","title":"WebQA: Multihop and Multimodal QA","created":"2021-09-01","cited_by_count":109},{"id":"1907.06390","title":"Sequence Level Semantics Aggregation for Video Object Detection","created":"2019-07-15","cited_by_count":87},{"id":"1801.02753","title":"SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis","created":"2018-01-09","cited_by_count":81},{"id":"1904.03451","title":"Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval","created":"2019-04-06","cited_by_count":79},{"id":"2201.05047","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2022-01-13","cited_by_count":78},{"id":"1602.08465","title":"Seq-NMS for Video Object Detection","created":"2016-02-26","cited_by_count":68},{"id":"1911.12529","title":"One-Shot Object Detection with Co-Attention and Co-Excitation","created":"2019-11-28","cited_by_count":67},{"id":"2105.06247","title":"Video Corpus Moment Retrieval with Contrastive Learning","created":"2021-05-13","cited_by_count":60},{"id":"2001.02600","title":"Deep Learning for Free-Hand Sketch: A Survey","created":"2020-01-08","cited_by_count":59},{"id":"2002.10310","title":"Sketch Less for More: On-the-Fly Fine-Grained Sketch Based Image Retrieval","created":"2020-02-24","cited_by_count":59},{"id":"2211.13916","title":"Towards Good Practices for Missing Modality Robust Action Recognition","created":"2022-11-25","cited_by_count":54},{"id":"2103.15706","title":"StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval","created":"2021-03-29","cited_by_count":50},{"id":"1707.06375","title":"3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks","created":"2017-07-20","cited_by_count":45},{"id":"1504.03504","title":"Sketch-based 3D Shape Retrieval using Convolutional Neural Networks","created":"2015-04-14","cited_by_count":41},{"id":"2105.10920","title":"End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2021-05-23","cited_by_count":40},{"id":"2001.02890","title":"Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches","created":"2020-01-09","cited_by_count":37},{"id":"2108.02774","title":"Sketch Your Own GAN","created":"2021-08-05","cited_by_count":37},{"id":"2003.06800","title":"OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features","created":"2020-03-15","cited_by_count":35},{"id":"1804.08972","title":"FaceShop: Deep Sketch-based Face Image Editing","created":"2018-04-24","cited_by_count":24},{"id":"2203.14843","title":"Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches","created":"2022-03-28","cited_by_count":23},{"id":"2008.06551","title":"Sketch-Guided Object Localization in Natural Images","created":"2020-08-14","cited_by_count":21},{"id":"2209.02242","title":"PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection","created":"2022-09-06","cited_by_count":17},{"id":"1703.07938","title":"Planar Object Tracking in the Wild: A Benchmark","created":"2017-03-23","cited_by_count":10},{"id":"2208.11314","title":"Modality Mixer for Multi-modal Action Recognition","created":"2022-08-24","cited_by_count":9},{"id":"2002.09461","title":"Fine-Grained Instance-Level Sketch-Based Video Retrieval","created":"2020-02-21","cited_by_count":6},{"id":"2109.11874","title":"Localizing Infinity-shaped fishes: Sketch-guided object localization in the wild","created":"2021-09-24","cited_by_count":3},{"id":"1304.5168","title":"Image Retrieval based on Bag-of-Words model","created":"2013-04-18","cited_by_count":1}],"next_cursor":null}