{"list":"other","total":55,"rows":[{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"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":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"1611.00850","title":"Optical Flow Estimation using a Spatial Pyramid Network","created":"2016-11-03","cited_by_count":424},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"id":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"2104.02409","title":"Learning to Estimate Hidden Motions with Global Motion Aggregation","created":"2021-04-06","cited_by_count":224},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2303.01943","title":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","created":"2023-03-03","cited_by_count":172},{"id":"1709.07322","title":"Playing for Benchmarks","created":"2017-09-21","cited_by_count":169},{"id":"2211.10408","title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","created":"2022-11-18","cited_by_count":166},{"id":"1904.09117","title":"SelFlow: Self-Supervised Learning of Optical Flow","created":"2019-04-19","cited_by_count":128},{"id":"2003.13045","title":"Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation","created":"2020-03-29","cited_by_count":120},{"id":"2306.01923","title":"The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation","created":"2023-06-02","cited_by_count":116},{"id":"2303.01237","title":"FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation","created":"2023-03-02","cited_by_count":114},{"id":"2202.12172","title":"Overcoming a Theoretical Limitation of Self-Attention","created":"2022-02-24","cited_by_count":113},{"id":"2009.01835","title":"Flow-edge Guided Video Completion","created":"2020-09-03","cited_by_count":104},{"id":"1606.07873","title":"An Uncertain Future: Forecasting from Static Images using Variational Autoencoders","created":"2016-06-25","cited_by_count":87},{"id":"2203.00867","title":"Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding","created":"2022-03-02","cited_by_count":83},{"id":"1711.11152","title":"Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition","created":"2017-11-29","cited_by_count":82},{"id":"2303.08340","title":"VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation","created":"2023-03-15","cited_by_count":82},{"id":"1501.02565","title":"EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow","created":"2015-01-12","cited_by_count":80},{"id":"2203.11335","title":"Global Matching with Overlapping Attention for Optical Flow Estimation","created":"2022-03-21","cited_by_count":64},{"id":"2104.04329","title":"Learning Position and Target Consistency for Memory-based Video Object Segmentation","created":"2021-04-09","cited_by_count":63},{"id":"2104.00924","title":"Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning","created":"2021-04-02","cited_by_count":62},{"id":"2205.14623","title":"SKFlow: Learning Optical Flow with Super Kernels","created":"2022-05-29","cited_by_count":56},{"id":"2205.03761","title":"Recurrent Dynamic Embedding for Video Object Segmentation","created":"2022-05-08","cited_by_count":52},{"id":"2102.08643","title":"Temporal Memory Attention for Video Semantic Segmentation","created":"2021-02-17","cited_by_count":50},{"id":"2204.00330","title":"DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow","created":"2022-04-01","cited_by_count":40},{"id":"1701.01821","title":"Unsupervised Learning of Long-Term Motion Dynamics for Videos","created":"2017-01-07","cited_by_count":37},{"id":"1810.10066","title":"A Fusion Approach for Multi-Frame Optical Flow Estimation","created":"2018-10-23","cited_by_count":37},{"id":"1505.00295","title":"Dense Optical Flow Prediction from a Static Image","created":"2015-05-02","cited_by_count":36},{"id":"2303.08384","title":"Rethinking Optical Flow from Geometric Matching Consistent Perspective","created":"2023-03-15","cited_by_count":33},{"id":"2206.13454","title":"Optimizing Video Prediction via Video Frame Interpolation","created":"2022-06-27","cited_by_count":28},{"id":"2101.01715","title":"Local Memory Attention for Fast Video Semantic Segmentation","created":"2021-01-05","cited_by_count":25},{"id":"2210.05950","title":"ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors","created":"2022-10-12","cited_by_count":21},{"id":"1711.03270","title":"Predicting Scene Parsing and Motion Dynamics in the Future","created":"2017-11-09","cited_by_count":20},{"id":"2108.11048","title":"Memory-Augmented Non-Local Attention for Video Super-Resolution","created":"2021-08-25","cited_by_count":17},{"id":"2104.09498","title":"Comparing Correspondences: Video Prediction with Correspondence-wise Losses","created":"2021-04-19","cited_by_count":16},{"id":"2208.01837","title":"Learning Prior Feature and Attention Enhanced Image Inpainting","created":"2022-08-03","cited_by_count":16},{"id":"2210.16900","title":"High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022)","created":"2022-10-30","cited_by_count":12},{"id":"2103.02996","title":"Optical Flow Estimation from a Single Motion-blurred Image","created":"2021-03-04","cited_by_count":11},{"id":"2211.08049","title":"Forecasting Future Instance Segmentation with Learned Optical Flow and Warping","created":"2022-11-15","cited_by_count":4}],"next_cursor":null}