{"list":"other","total":83,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"1504.06375","title":"Holistically-Nested Edge Detection","created":"2015-04-24","cited_by_count":592},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"1905.06922","title":"On Variational Bounds of Mutual Information","created":"2019-05-16","cited_by_count":559},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"1505.00853","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","created":"2015-05-05","cited_by_count":519},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1812.00101","title":"DVC: An End-to-end Deep Video Compression Framework","created":"2018-11-30","cited_by_count":332},{"id":"2110.13903","title":"NeRV: Neural Representations for Videos","created":"2021-10-26","cited_by_count":256},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229},{"id":"2109.15047","title":"Deep Contextual Video Compression","created":"2021-09-30","cited_by_count":221},{"id":"1611.05594","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","created":"2016-11-17","cited_by_count":219},{"id":"2304.01247","title":"Generative Diffusion Prior for Unified Image Restoration and Enhancement","created":"2023-04-03","cited_by_count":199},{"id":"2302.14402","title":"Neural Video Compression with Diverse Contexts","created":"2023-02-28","cited_by_count":165},{"id":"2105.09600","title":"FVC: A New Framework towards Deep Video Compression in Feature Space","created":"2021-05-20","cited_by_count":153},{"id":"2207.05894","title":"Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression","created":"2022-07-13","cited_by_count":128},{"id":"2402.17414","title":"Neural Video Compression with Feature Modulation","created":"2024-02-27","cited_by_count":123},{"id":"2004.10290","title":"M-LVC: Multiple Frames Prediction for Learned Video Compression","created":"2020-04-21","cited_by_count":107},{"id":"1712.00636","title":"Compressed Video Action Recognition","created":"2017-12-02","cited_by_count":106},{"id":"2001.03569","title":"Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics","created":"2020-01-10","cited_by_count":80},{"id":"2207.08132","title":"E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context","created":"2022-07-17","cited_by_count":76},{"id":"2206.07307","title":"VCT: A Video Compression Transformer","created":"2022-06-15","cited_by_count":74},{"id":"2003.11282","title":"Content Adaptive and Error Propagation Aware Deep Video Compression","created":"2020-03-25","cited_by_count":72},{"id":"2107.08373","title":"Scalable Image Coding for Humans and Machines","created":"2021-07-18","cited_by_count":66},{"id":"2207.07116","title":"Bootstrapped Masked Autoencoders for Vision BERT Pretraining","created":"2022-07-14","cited_by_count":60},{"id":"2206.07460","title":"Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Prediction","created":"2022-06-15","cited_by_count":55},{"id":"2106.10800","title":"Lossy Compression for Lossless Prediction","created":"2021-06-21","cited_by_count":52},{"id":"2007.11797","title":"End-to-end Learning of Compressible Features","created":"2020-07-23","cited_by_count":43},{"id":"2109.03082","title":"Perceptual Learned Video Compression with Recurrent Conditional GAN","created":"2021-09-07","cited_by_count":41},{"id":"2308.10794","title":"MGMAE: Motion Guided Masking for Video Masked Autoencoding","created":"2023-08-21","cited_by_count":41},{"id":"2210.06096","title":"Masked Motion Encoding for Self-Supervised Video Representation Learning","created":"2022-10-12","cited_by_count":39},{"id":"1901.03460","title":"DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition","created":"2019-01-11","cited_by_count":36},{"id":"2110.06513","title":"Benchmarking the Robustness of Spatial-Temporal Models Against Corruptions","created":"2021-10-13","cited_by_count":34},{"id":"1811.11057","title":"Fast Object Detection in Compressed Video","created":"2018-11-27","cited_by_count":33},{"id":"2001.02915","title":"Towards Coding for Human and Machine Vision: A Scalable Image Coding Approach","created":"2020-01-09","cited_by_count":31},{"id":"2207.01932","title":"Image Coding for Machines with Omnipotent Feature Learning","created":"2022-07-05","cited_by_count":31},{"id":"1806.03348","title":"DSSLIC: Deep Semantic Segmentation-based Layered Image Compression","created":"2018-06-08","cited_by_count":27},{"id":"1710.11151","title":"High efficiency compression for object detection","created":"2017-10-30","cited_by_count":24},{"id":"2104.10315","title":"Visual Analysis Motivated Rate-Distortion Model for Image Coding","created":"2021-04-21","cited_by_count":21},{"id":"1704.08141","title":"Compact Descriptors for Video Analysis: the Emerging MPEG Standard","created":"2017-04-26","cited_by_count":20},{"id":"2210.04154","title":"Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders","created":"2022-10-09","cited_by_count":20},{"id":"2204.05308","title":"On the Generalization of BasicVSR++ to Video Deblurring and Denoising","created":"2022-04-11","cited_by_count":19},{"id":"1804.09963","title":"Near-Lossless Deep Feature Compression for Collaborative Intelligence","created":"2018-04-26","cited_by_count":17},{"id":"2105.10089","title":"Latent-space scalability for multi-task collaborative intelligence","created":"2021-05-21","cited_by_count":17},{"id":"2202.02813","title":"A Coding Framework and Benchmark towards Low-Bitrate Video Understanding","created":"2022-02-06","cited_by_count":17},{"id":"2107.10771","title":"EAN: Event Adaptive Network for Enhanced Action Recognition","created":"2021-07-22","cited_by_count":16},{"id":"2203.15336","title":"End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection","created":"2022-03-29","cited_by_count":16},{"id":"2011.04976","title":"Conceptual Compression via Deep Structure and Texture Synthesis","created":"2020-11-10","cited_by_count":14},{"id":"2306.10681","title":"VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision","created":"2023-06-19","cited_by_count":13},{"id":"2405.20666","title":"MASA: Motion-aware Masked Autoencoder with Semantic Alignment for Sign Language Recognition","created":"2024-05-31","cited_by_count":13},{"id":"2210.05234","title":"It Takes Two: Masked Appearance-Motion Modeling for Self-supervised Video Transformer Pre-training","created":"2022-10-11","cited_by_count":10},{"id":"2103.07131","title":"Thousand to One: Semantic Prior Modeling for Conceptual Coding","created":"2021-03-12","cited_by_count":9},{"id":"2404.04848","title":"Task-Aware Encoder Control for Deep Video Compression","created":"2024-04-07","cited_by_count":6},{"id":"2202.00892","title":"Does Video Compression Impact Tracking Accuracy?","created":"2022-02-02","cited_by_count":4},{"id":"2005.12810","title":"JPD-SE: High-Level Semantics for Joint Perception-Distortion Enhancement in Image Compression","created":"2020-05-24","cited_by_count":3},{"id":"1502.07828","title":"Hybrid coding of visual content and local image features","created":"2015-02-27","cited_by_count":2}],"next_cursor":null}