{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1901.08971","title":"FaceForensics++: Learning to Detect Manipulated Facial Images","created":"2019-01-25","cited_by_count":1101},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"1909.12962","title":"Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics","created":"2019-09-27","cited_by_count":575},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"1912.13458","title":"Face X-ray for More General Face Forgery Detection","created":"2019-12-31","cited_by_count":470},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"2103.02406","title":"Multi-attentional Deepfake Detection","created":"2021-03-03","cited_by_count":341},{"id":"1811.00656","title":"Exposing DeepFake Videos By Detecting Face Warping Artifacts","created":"2018-11-01","cited_by_count":319},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310},{"id":"2012.07657","title":"Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection","created":"2020-12-14","cited_by_count":287},{"id":"2103.12376","title":"Generalizing Face Forgery Detection with High-frequency Features","created":"2021-03-23","cited_by_count":262},{"id":"2103.01856","title":"Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain","created":"2021-03-02","cited_by_count":244},{"id":"2101.01456","title":"WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection","created":"2021-01-05","cited_by_count":209},{"id":"1810.11215","title":"Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videos","created":"2018-10-26","cited_by_count":180},{"id":"2003.00392","title":"Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning","created":"2020-03-01","cited_by_count":180},{"id":"2012.09311","title":"Learning Self-Consistency for Deepfake Detection","created":"2020-12-16","cited_by_count":179},{"id":"2007.10247","title":"Learning Joint Spatial-Temporal Transformations for Video Inpainting","created":"2020-07-20","cited_by_count":163},{"id":"2102.07074","title":"TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up","created":"2021-02-14","cited_by_count":162},{"id":"2004.04467","title":"Adversarial Latent Autoencoders","created":"2020-04-09","cited_by_count":155},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"1908.02486","title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","created":"2019-08-07","cited_by_count":142},{"id":"2103.09096","title":"Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection","created":"2021-03-16","cited_by_count":134},{"id":"1702.00758","title":"HashNet: Deep Learning to Hash by Continuation","created":"2017-02-02","cited_by_count":122},{"id":"1611.09577","title":"Fast Face-swap Using Convolutional Neural Networks","created":"2016-11-29","cited_by_count":119},{"id":"1905.02884","title":"Deep Flow-Guided Video Inpainting","created":"2019-05-08","cited_by_count":116},{"id":"2003.03772","title":"IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval","created":"2020-03-08","cited_by_count":115},{"id":"2107.04589","title":"ViTGAN: Training GANs with Vision Transformers","created":"2021-07-09","cited_by_count":110},{"id":"1905.01639","title":"Deep Video Inpainting","created":"2019-05-05","cited_by_count":109},{"id":"2104.06609","title":"Representative Forgery Mining for Fake Face Detection","created":"2021-04-14","cited_by_count":108},{"id":"2009.01835","title":"Flow-edge Guided Video Completion","created":"2020-09-03","cited_by_count":104},{"id":"2007.12163","title":"Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval","created":"2020-07-23","cited_by_count":98},{"id":"2012.02512","title":"ID-Reveal: Identity-aware DeepFake Video Detection","created":"2020-12-04","cited_by_count":97},{"id":"2109.02974","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","created":"2021-09-07","cited_by_count":95},{"id":"1911.09435","title":"TEINet: Towards an Efficient Architecture for Video Recognition","created":"2019-11-21","cited_by_count":92},{"id":"1611.02155","title":"Spatiotemporal Residual Networks for Video Action Recognition","created":"2016-11-07","cited_by_count":91},{"id":"1808.05174","title":"Recycle-GAN: Unsupervised Video Retargeting","created":"2018-08-15","cited_by_count":89},{"id":"2109.01860","title":"Spatiotemporal Inconsistency Learning for DeepFake Video Detection","created":"2021-09-04","cited_by_count":88},{"id":"2108.11353","title":"Multi-Task Self-Training for Learning General Representations","created":"2021-08-25","cited_by_count":85},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84},{"id":"1908.00347","title":"Central Similarity Quantization for Efficient Image and Video Retrieval","created":"2019-08-01","cited_by_count":77},{"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":"1908.11587","title":"Copy-and-Paste Networks for Deep Video Inpainting","created":"2019-08-30","cited_by_count":58},{"id":"2104.04480","title":"Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features","created":"2021-04-09","cited_by_count":57},{"id":"2112.03553","title":"ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images","created":"2021-12-07","cited_by_count":48},{"id":"1908.08718","title":"Onion-Peel Networks for Deep Video Completion","created":"2019-08-23","cited_by_count":46},{"id":"1912.08967","title":"Fashion Outfit Complementary Item Retrieval","created":"2019-12-19","cited_by_count":42},{"id":"2001.09598","title":"FakeLocator: Robust Localization of GAN-Based Face Manipulations","created":"2020-01-27","cited_by_count":40},{"id":"2103.13990","title":"More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval","created":"2021-03-25","cited_by_count":38},{"id":"2108.05307","title":"Video Transformer for Deepfake Detection with Incremental Learning","created":"2021-08-11","cited_by_count":33},{"id":"2002.11930","title":"Auto-Encoding Twin-Bottleneck Hashing","created":"2020-02-27","cited_by_count":26},{"id":"2004.00280","title":"Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal Hashing","created":"2020-04-01","cited_by_count":26},{"id":"2108.03871","title":"TransForensics: Image Forgery Localization with Dense Self-Attention","created":"2021-08-09","cited_by_count":26},{"id":"1705.09765","title":"Deep Matching and Validation Network -- An End-to-End Solution to Constrained Image Splicing Localization and Detection","created":"2017-05-27","cited_by_count":25},{"id":"2107.02434","title":"Self-Adversarial Training incorporating Forgery Attention for Image Forgery Localization","created":"2021-07-06","cited_by_count":24},{"id":"2002.11281","title":"Generalized Product Quantization Network for Semi-supervised Image Retrieval","created":"2020-02-26","cited_by_count":20},{"id":"2007.08617","title":"Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval","created":"2020-07-16","cited_by_count":20},{"id":"2008.01369","title":"ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image Retrieval","created":"2020-08-04","cited_by_count":16},{"id":"2105.05332","title":"The DEVIL is in the Details: A Diagnostic Evaluation Benchmark for Video Inpainting","created":"2021-05-11","cited_by_count":12},{"id":"2101.11080","title":"Deep Video Inpainting Detection","created":"2021-01-26","cited_by_count":11},{"id":"2003.03293","title":"Probability Weighted Compact Feature for Domain Adaptive Retrieval","created":"2020-03-06","cited_by_count":9},{"id":"2109.12564","title":"Vision Transformer Hashing for Image Retrieval","created":"2021-09-26","cited_by_count":9},{"id":"2106.01532","title":"Noise Doesn't Lie: Towards Universal Detection of Deep Inpainting","created":"2021-06-03","cited_by_count":8}],"next_cursor":null}