{"list":"other","total":54,"rows":[{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1808.00449","title":"Learning Blind Video Temporal Consistency","created":"2018-08-01","cited_by_count":253},{"id":"1809.00461","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","created":"2018-09-03","cited_by_count":232},{"id":"2303.11950","title":"Learning A Sparse Transformer Network for Effective Image Deraining","created":"2023-03-21","cited_by_count":205},{"id":"2403.06976","title":"BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion","created":"2024-03-11","cited_by_count":202},{"id":"2309.03897","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","created":"2023-09-07","cited_by_count":197},{"id":"2007.10247","title":"Learning Joint Spatial-Temporal Transformations for Video Inpainting","created":"2020-07-20","cited_by_count":163},{"id":"1905.02884","title":"Deep Flow-Guided Video Inpainting","created":"2019-05-08","cited_by_count":116},{"id":"2204.02663","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","created":"2022-04-06","cited_by_count":113},{"id":"2009.01835","title":"Flow-edge Guided Video Completion","created":"2020-09-03","cited_by_count":104},{"id":"2109.02974","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","created":"2021-09-07","cited_by_count":95},{"id":"1904.10247","title":"Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN","created":"2019-04-23","cited_by_count":87},{"id":"2210.02025","title":"GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models","created":"2022-10-05","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":"1810.08771","title":"Image Inpainting via Generative Multi-column Convolutional Neural Networks","created":"2018-10-20","cited_by_count":81},{"id":"2105.08468","title":"Progressively Normalized Self-Attention Network for Video Polyp Segmentation","created":"2021-05-18","cited_by_count":75},{"id":"2501.10018","title":"DiffuEraser: A Diffusion Model for Video Inpainting","created":"2025-01-17","cited_by_count":72},{"id":"2005.03337","title":"Wavelet Integrated CNNs for Noise-Robust Image Classification","created":"2020-05-07","cited_by_count":60},{"id":"2208.06768","title":"Flow-Guided Transformer for Video Inpainting","created":"2022-08-14","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":"2403.05234","title":"Benchmarking Micro-action Recognition: Dataset, Methods, and Applications","created":"2024-03-08","cited_by_count":48},{"id":"1908.08718","title":"Onion-Peel Networks for Deep Video Completion","created":"2019-08-23","cited_by_count":46},{"id":"2203.09773","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","created":"2022-03-18","cited_by_count":41},{"id":"2403.19898","title":"Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpainting","created":"2024-03-29","cited_by_count":40},{"id":"2410.12332","title":"MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs","created":"2024-10-16","cited_by_count":39},{"id":"2205.05076","title":"Reduce Information Loss in Transformers for Pluralistic Image Inpainting","created":"2022-05-10","cited_by_count":36},{"id":"2009.05721","title":"Short-Term and Long-Term Context Aggregation Network for Video Inpainting","created":"2020-09-12","cited_by_count":35},{"id":"2104.03507","title":"Progressive Temporal Feature Alignment Network for Video Inpainting","created":"2021-04-08","cited_by_count":35},{"id":"2203.06304","title":"MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting","created":"2022-03-12","cited_by_count":35},{"id":"1909.07957","title":"An Internal Learning Approach to Video Inpainting","created":"2019-09-17","cited_by_count":33},{"id":"2401.10226","title":"Towards Language-Driven Video Inpainting via Multimodal Large Language Models","created":"2024-01-18","cited_by_count":33},{"id":"2107.13335","title":"WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification","created":"2021-07-28","cited_by_count":29},{"id":"2308.12595","title":"Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation","created":"2023-08-24","cited_by_count":29},{"id":"2003.06816","title":"VCNet: A Robust Approach to Blind Image Inpainting","created":"2020-03-15","cited_by_count":25},{"id":"2308.06009","title":"ViGT: Proposal-free Video Grounding with Learnable Token in Transformer","created":"2023-08-11","cited_by_count":22},{"id":"2412.14719","title":"Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition","created":"2024-12-19","cited_by_count":22},{"id":"2408.11402","title":"Video Diffusion Models are Strong Video Inpainter","created":"2024-08-21","cited_by_count":21},{"id":"2207.10391","title":"Error Compensation Framework for Flow-Guided Video Inpainting","created":"2022-07-21","cited_by_count":20},{"id":"2407.05311","title":"MMAD: Multi-label Micro-Action Detection in Videos","created":"2024-07-07","cited_by_count":20},{"id":"2407.04490","title":"Micro-gesture Online Recognition using Learnable Query Points","created":"2024-07-05","cited_by_count":18},{"id":"2208.01837","title":"Learning Prior Feature and Attention Enhanced Image Inpainting","created":"2022-08-03","cited_by_count":16},{"id":"2308.01526","title":"Data Augmentation for Human Behavior Analysis in Multi-Person Conversations","created":"2023-08-03","cited_by_count":15},{"id":"2209.13925","title":"DeViT: Deformed Vision Transformers in Video Inpainting","created":"2022-09-28","cited_by_count":13},{"id":"2412.07233","title":"Repetitive Action Counting with Hybrid Temporal Relation Modeling","created":"2024-12-10","cited_by_count":13},{"id":"2412.08975","title":"Elevating Flow-Guided Video Inpainting with Reference Generation","created":"2024-12-12","cited_by_count":9},{"id":"1712.09078","title":"Deep Blind Image Inpainting","created":"2017-12-25","cited_by_count":8},{"id":"1905.02949","title":"Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence","created":"2019-05-08","cited_by_count":8},{"id":"2208.06807","title":"Semi-Supervised Video Inpainting with Cycle Consistency Constraints","created":"2022-08-14","cited_by_count":8},{"id":"2403.18186","title":"Don't Look into the Dark: Latent Codes for Pluralistic Image Inpainting","created":"2024-03-27","cited_by_count":6},{"id":"2302.14362","title":"One-Shot Video Inpainting","created":"2023-02-28","cited_by_count":3},{"id":"2111.03574","title":"Spatial-Temporal Residual Aggregation for High Resolution Video Inpainting","created":"2021-11-05","cited_by_count":2},{"id":"2501.15043","title":"Prompt-Aware Controllable Shadow Removal","created":"2025-01-25","cited_by_count":2},{"id":"2205.06597","title":"Blind Image Inpainting with Sparse Directional Filter Dictionaries for Lightweight CNNs","created":"2022-05-13","cited_by_count":1},{"id":"2311.04261","title":"Restoration of Analog Videos Using Swin-UNet","created":"2023-11-07","cited_by_count":1}],"next_cursor":null}