{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/video-segmentation/papers/3","list_of":"/task/video-segmentation","task":"Video Segmentation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":4,"rows_per_page":100,"rows":[201,300],"of":388,"counts":{"archive_papers_tagged":388,"with_a_code_link":160,"where_syntology_ran_a_sample":46,"not_listed_spam_title":0,"listed":388,"listed_where_code_ran":46,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":40,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":40,"listed_every_run_a_failure_of_syntologys_instrument":6,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/video-segmentation","prev":"/task/video-segmentation/papers/2","next":"/task/video-segmentation/papers/4","papers":[{"url":null,"slug":"lsvos-challenge-report-large-scale-complex","title":"LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation","date":"2024-09-09","arxiv_id":"2409.05847","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-video-segmentation-with-masked","title":"Rethinking Video Segmentation with Masked Video Consistency: Did the Model Learn as Intended?","date":"2024-08-20","arxiv_id":"2408.10627","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-object-segmentation-via-sam-2-the-4th","title":"Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track","date":"2024-08-19","arxiv_id":"2408.10125","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-sam-2-better-than-sam-in-medical-image","title":"Is SAM 2 Better than SAM in Medical Image Segmentation?","date":"2024-08-08","arxiv_id":"2408.04212","repositories_listed":0,"syntology":null},{"url":null,"slug":"novel-adaptation-of-video-segmentation-to-3d","title":"Novel adaptation of video segmentation to 3D MRI: efficient zero-shot knee segmentation with SAM2","date":"2024-08-08","arxiv_id":"2408.04762","repositories_listed":0,"syntology":null},{"url":null,"slug":"saliency-detection-in-educational-videos","title":"Saliency Detection in Educational Videos: Analyzing the Performance of Current Models, Identifying Limitations and Advancement Directions","date":"2024-08-08","arxiv_id":"2408.04515","repositories_listed":0,"syntology":null},{"url":null,"slug":"sam-2-in-robotic-surgery-an-empirical","title":"SAM 2 in Robotic Surgery: An Empirical Evaluation for Robustness and Generalization in Surgical Video Segmentation","date":"2024-08-08","arxiv_id":"2408.04593","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-and-non-adversarial-robustness-of","title":"Performance and Non-adversarial Robustness of the Segment Anything Model 2 in Surgical Video Segmentation","date":"2024-08-07","arxiv_id":"2408.04098","repositories_listed":0,"syntology":null},{"url":null,"slug":"foodmem-near-real-time-and-precise-food-video","title":"FoodMem: Near Real-time and Precise Food Video Segmentation","date":"2024-07-16","arxiv_id":"2407.12121","repositories_listed":0,"syntology":null},{"url":null,"slug":"dabit-depth-and-blur-informed-transformer-for","title":"DaBiT: Depth and Blur informed Transformer for Joint Refocusing and Super-Resolution","date":"2024-07-01","arxiv_id":"2407.01230","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-unfolding-aided-parameter-tuning-for","title":"Deep Unfolding-Aided Parameter Tuning for Plug-and-Play-Based Video Snapshot Compressive Imaging","date":"2024-06-28","arxiv_id":"2406.19870","repositories_listed":0,"syntology":null},{"url":null,"slug":"missiongnn-hierarchical-multimodal-gnn-based","title":"MissionGNN: Hierarchical Multimodal GNN-based Weakly Supervised Video Anomaly Recognition with Mission-Specific Knowledge Graph Generation","date":"2024-06-27","arxiv_id":"2406.18815","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-segmentation-for-vocal-tract","title":"Multimodal Segmentation for Vocal Tract Modeling","date":"2024-06-22","arxiv_id":"2406.15754","repositories_listed":0,"syntology":null},{"url":null,"slug":"2nd-place-solution-for-mevis-track-in-cvpr","title":"2nd Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation","date":"2024-06-20","arxiv_id":"2406.13939","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-representation-learning-with-1","title":"Visual Representation Learning with Stochastic Frame Prediction","date":"2024-06-11","arxiv_id":"2406.07398","repositories_listed":0,"syntology":null},{"url":null,"slug":"i-mpn-inductive-message-passing-network-for","title":"I-MPN: Inductive Message Passing Network for Efficient Human-in-the-Loop Annotation of Mobile Eye Tracking Data","date":"2024-06-10","arxiv_id":"2406.06239","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-free-robust-interactive-video-object","title":"Training-Free Robust Interactive Video Object Segmentation","date":"2024-06-08","arxiv_id":"2406.05485","repositories_listed":0,"syntology":null},{"url":null,"slug":"3rd-place-solution-for-mevis-track-in-cvpr","title":"3rd Place Solution for MeViS Track in CVPR 2024 PVUW workshop: Motion Expression guided Video Segmentation","date":"2024-06-07","arxiv_id":"2406.04842","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-dance-video-segmentation-for","title":"Automatic Dance Video Segmentation for Understanding Choreography","date":"2024-05-30","arxiv_id":"2405.19727","repositories_listed":0,"syntology":null},{"url":null,"slug":"triple-component-matrix-factorization","title":"Triple Component Matrix Factorization: Untangling Global, Local, and Noisy Components","date":"2024-03-21","arxiv_id":"2404.07955","repositories_listed":0,"syntology":null},{"url":null,"slug":"motion-corrected-moving-average-including","title":"Motion-Corrected Moving Average: Including Post-Hoc Temporal Information for Improved Video Segmentation","date":"2024-03-05","arxiv_id":"2403.03120","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-two-shot-all-you-need-a-label-efficient","title":"Is Two-shot All You Need? A Label-efficient Approach for Video Segmentation in Breast Ultrasound","date":"2024-02-07","arxiv_id":"2402.04921","repositories_listed":0,"syntology":null},{"url":null,"slug":"appearance-based-refinement-for-object","title":"Appearance-Based Refinement for Object-Centric Motion Segmentation","date":"2023-12-18","arxiv_id":"2312.11463","repositories_listed":0,"syntology":null},{"url":null,"slug":"gendef-learning-generative-deformation-field","title":"GenDeF: Learning Generative Deformation Field for Video Generation","date":"2023-12-07","arxiv_id":"2312.04561","repositories_listed":0,"syntology":null},{"url":null,"slug":"deeppyramid-medical-image-segmentation-using","title":"DeepPyramid+: Medical Image Segmentation using Pyramid View Fusion and Deformable Pyramid Reception","date":"2023-12-06","arxiv_id":"2312.03409","repositories_listed":0,"syntology":null},{"url":null,"slug":"correlation-aware-active-learning-for-surgery","title":"Correlation-aware active learning for surgery video segmentation","date":"2023-11-15","arxiv_id":"2311.08811","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-video-transformers-for","title":"Understanding Video Transformers for Segmentation: A Survey of Application and Interpretability","date":"2023-10-18","arxiv_id":"2310.12296","repositories_listed":0,"syntology":null},{"url":null,"slug":"coralvos-dataset-and-benchmark-for-coral","title":"CoralVOS: Dataset and Benchmark for Coral Video Segmentation","date":"2023-10-03","arxiv_id":"2310.01946","repositories_listed":0,"syntology":null},{"url":null,"slug":"unilvseg-unified-left-ventricular","title":"SimLVSeg: Simplifying Left Ventricular Segmentation in 2D+Time Echocardiograms with Self- and Weakly-Supervised Learning","date":"2023-09-30","arxiv_id":"2310.00454","repositories_listed":0,"syntology":null},{"url":null,"slug":"sanpo-a-scene-understanding-accessibility","title":"SANPO: A Scene Understanding, Accessibility and Human Navigation Dataset","date":"2023-09-21","arxiv_id":"2309.12172","repositories_listed":0,"syntology":null},{"url":null,"slug":"mega-multimodal-alignment-aggregation-and","title":"MEGA: Multimodal Alignment Aggregation and Distillation For Cinematic Video Segmentation","date":"2023-08-22","arxiv_id":"2308.11185","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-environment-mapping-and-immersive","title":"Immersive Human-Machine Teleoperation Framework for Precision Agriculture: Integrating UAV-based Digital Mapping and Virtual Reality Control","date":"2023-08-14","arxiv_id":"2308.07231","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-segment-anything-model-sam-vision","title":"A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering","date":"2023-05-12","arxiv_id":"2306.06211","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-interaction-and-activity","title":"Automatic Interaction and Activity Recognition from Videos of Human Manual Demonstrations with Application to Anomaly Detection","date":"2023-04-19","arxiv_id":"2304.09789","repositories_listed":0,"syntology":null},{"url":null,"slug":"med-vt-multiscale-encoder-decoder-video","title":"MED-VT++: Unifying Multimodal Learning with a Multiscale Encoder-Decoder Video Transformer","date":"2023-04-12","arxiv_id":"2304.05930","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-threefold-review-on-deep-semantic","title":"A Threefold Review on Deep Semantic Segmentation: Efficiency-oriented, Temporal and Depth-aware design","date":"2023-03-08","arxiv_id":"2303.04315","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-adapt-to-online-streams-with","title":"Learning to Adapt to Online Streams with Distribution Shifts","date":"2023-03-02","arxiv_id":"2303.01630","repositories_listed":0,"syntology":null},{"url":null,"slug":"approximating-dtw-with-a-convolutional-neural","title":"Approximating DTW with a convolutional neural network on EEG data","date":"2023-01-30","arxiv_id":"2301.12873","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-review-of-modern-object","title":"A Comprehensive Review of Modern Object Segmentation Approaches","date":"2023-01-13","arxiv_id":"2301.07499","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-segmentation-with-audio-context","title":"Object Segmentation with Audio Context","date":"2023-01-04","arxiv_id":"2301.10295","repositories_listed":0,"syntology":null},{"url":null,"slug":"newsnet-a-novel-dataset-for-hierarchical","title":"NewsNet: A Novel Dataset for Hierarchical Temporal Segmentation","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"video-segmentation-learning-using-cascade","title":"Video Segmentation Learning Using Cascade Residual Convolutional Neural Network","date":"2022-12-20","arxiv_id":"2212.10570","repositories_listed":0,"syntology":null},{"url":null,"slug":"tencent-avs-a-holistic-ads-video-dataset-for","title":"Tencent AVS: A Holistic Ads Video Dataset for Multi-modal Scene Segmentation","date":"2022-12-09","arxiv_id":"2212.04700","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-product-of-experts-for-learning","title":"Generalized Product-of-Experts for Learning Multimodal Representations in Noisy Environments","date":"2022-11-07","arxiv_id":"2211.03587","repositories_listed":0,"syntology":null},{"url":"/paper/motion-inductive-self-supervised-object","slug":"motion-inductive-self-supervised-object","title":"Motion-inductive Self-supervised Object Discovery in Videos","date":"2022-10-01","arxiv_id":"2210.00221","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-heterogeneous-video-segmentation-at","title":"Efficient Heterogeneous Video Segmentation at the Edge","date":"2022-08-24","arxiv_id":"2208.11666","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-based","title":"Hierarchical Reinforcement Learning Based Video Semantic Coding for Segmentation","date":"2022-08-24","arxiv_id":"2208.11529","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-subtitle-feature-enhanced-video","title":"Visual Subtitle Feature Enhanced Video Outline Generation","date":"2022-08-24","arxiv_id":"2208.11307","repositories_listed":0,"syntology":null},{"url":null,"slug":"mac-do-charge-based-multi-bit-analog-in","title":"MAC-DO: An Efficient Output-Stationary GEMM Accelerator for CNNs Using DRAM Technology","date":"2022-07-16","arxiv_id":"2207.07862","repositories_listed":0,"syntology":null},{"url":null,"slug":"5th-place-solution-for-youtube-vos-challenge","title":"5th Place Solution for YouTube-VOS Challenge 2022: Video Object Segmentation","date":"2022-06-20","arxiv_id":"2206.09585","repositories_listed":0,"syntology":null},{"url":null,"slug":"distortion-aware-network-pruning-and-feature","title":"Distortion-Aware Network Pruning and Feature Reuse for Real-time Video Segmentation","date":"2022-06-20","arxiv_id":"2206.09604","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-machine-learning-based-segmentation","title":"A Machine Learning-based Segmentation Approach for Measuring Similarity between Sign Languages","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tubeformer-deeplab-video-mask-transformer","title":"TubeFormer-DeepLab: Video Mask Transformer","date":"2022-05-30","arxiv_id":"2205.15361","repositories_listed":0,"syntology":null},{"url":"/paper/guess-what-moves-unsupervised-video-and-image","slug":"guess-what-moves-unsupervised-video-and-image","title":"Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion","date":"2022-05-16","arxiv_id":"2205.07844","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-convolutional-networks-for-action","title":"3D Convolutional Networks for Action Recognition: Application to Sport Gesture Recognition","date":"2022-04-13","arxiv_id":"2204.08460","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-instance-segmentation-and-tracking-via","title":"Human Instance Segmentation and Tracking via Data Association and Single-stage Detector","date":"2022-03-31","arxiv_id":"2203.16966","repositories_listed":0,"syntology":null},{"url":"/paper/deeply-interleaved-two-stream-encoder-for","slug":"deeply-interleaved-two-stream-encoder-for","title":"Deeply Interleaved Two-Stream Encoder for Referring Video Segmentation","date":"2022-03-30","arxiv_id":"2203.15969","repositories_listed":0,"syntology":null},{"url":null,"slug":"dnn-driven-compressive-offloading-for-edge","title":"DNN-Driven Compressive Offloading for Edge-Assisted Semantic Video Segmentation","date":"2022-03-28","arxiv_id":"2203.14481","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-video-segmentation-models-with-per","title":"Efficient Video Segmentation Models with Per-frame Inference","date":"2022-02-24","arxiv_id":"2202.12427","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-accurate-and-consistent-video","title":"Real-Time, Accurate, and Consistent Video Semantic Segmentation via Unsupervised Adaptation and Cross-Unit Deployment on Mobile Device","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"youmvos-an-actor-centric-multi-shot-video","title":"YouMVOS: An Actor-Centric Multi-Shot Video Object Segmentation Dataset","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"perceptual-consistency-in-video-segmentation","title":"Perceptual Consistency in Video Segmentation","date":"2021-10-24","arxiv_id":"2110.12385","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporally-stable-video-segmentation-without","title":"Temporally stable video segmentation without video annotations","date":"2021-10-17","arxiv_id":"2110.08893","repositories_listed":0,"syntology":null},{"url":null,"slug":"viseret-a-simple-yet-effective-approach-to","title":"ViSeRet: A simple yet effective approach to moment retrieval via fine-grained video segmentation","date":"2021-10-11","arxiv_id":"2110.05146","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-better-segment-objects-from","title":"Learning to Better Segment Objects from Unseen Classes with Unlabeled Videos","date":"2021-04-25","arxiv_id":"2104.12276","repositories_listed":0,"syntology":null},{"url":"/paper/self-supervised-video-object-segmentation-by","slug":"self-supervised-video-object-segmentation-by","title":"Self-supervised Video Object Segmentation by Motion Grouping","date":"2021-04-15","arxiv_id":"2104.07658","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-automated-2d-and-3d-convolutional","title":"Fully Automated 2D and 3D Convolutional Neural Networks Pipeline for Video Segmentation and Myocardial Infarction Detection in Echocardiography","date":"2021-03-26","arxiv_id":"2103.14734","repositories_listed":0,"syntology":null},{"url":"/paper/clawcranenet-leveraging-object-level-relation","slug":"clawcranenet-leveraging-object-level-relation","title":"ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation","date":"2021-03-19","arxiv_id":"2103.10702","repositories_listed":0,"syntology":null},{"url":null,"slug":"novel-tile-segmentation-scheme-for","title":"Novel tile segmentation scheme for omnidirectional video","date":"2021-03-10","arxiv_id":"2103.05858","repositories_listed":0,"syntology":null},{"url":"/paper/referring-segmentation-in-images-and-videos","slug":"referring-segmentation-in-images-and-videos","title":"Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network","date":"2021-02-09","arxiv_id":"2102.04762","repositories_listed":0,"syntology":null},{"url":null,"slug":"videoclick-video-object-segmentation-with-a","title":"VideoClick: Video Object Segmentation with a Single Click","date":"2021-01-16","arxiv_id":"2101.06545","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-video-segmentation-for","title":"Semantic Video Segmentation for Intracytoplasmic Sperm Injection Procedures","date":"2021-01-04","arxiv_id":"2101.01207","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-fidelity-interactive-video-segmentation","title":"High Fidelity Interactive Video Segmentation Using Tensor Decomposition Boundary Loss Convolutional Tessellations and Context Aware Skip Connections","date":"2020-11-23","arxiv_id":"2011.11602","repositories_listed":0,"syntology":null},{"url":"/paper/actor-and-action-modular-network-for-text","slug":"actor-and-action-modular-network-for-text","title":"Actor and Action Modular Network for Text-based Video Segmentation","date":"2020-11-02","arxiv_id":"2011.00786","repositories_listed":0,"syntology":null},{"url":null,"slug":"highway-driving-dataset-for-semantic-video","title":"Highway Driving Dataset for Semantic Video Segmentation","date":"2020-11-02","arxiv_id":"2011.00674","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-video-segmentation-for-autonomous","title":"Semantic video segmentation for autonomous driving","date":"2020-10-28","arxiv_id":"2010.15250","repositories_listed":0,"syntology":null},{"url":null,"slug":"coherent-loss-a-generic-framework-for-stable","title":"Coherent Loss: A Generic Framework for Stable Video Segmentation","date":"2020-10-25","arxiv_id":"2010.13085","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-localized-photorealistic-video","title":"Real-time Localized Photorealistic Video Style Transfer","date":"2020-10-20","arxiv_id":"2010.10056","repositories_listed":0,"syntology":null},{"url":null,"slug":"noisy-lstm-improving-temporal-awareness-for","title":"Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation","date":"2020-10-19","arxiv_id":"2010.09466","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-motion-representation-via","title":"Self-supervised Motion Representation via Scattering Local Motion Cues","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deu-net-deformable-u-net-for-3d-cardiac-mri","title":"DeU-Net: Deformable U-Net for 3D Cardiac MRI Video Segmentation","date":"2020-07-13","arxiv_id":"2007.06341","repositories_listed":0,"syntology":null},{"url":null,"slug":"d3s-a-discriminative-single-shot-segmentation-1","title":"D3S - A Discriminative Single Shot Segmentation Tracker","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"video-instance-segmentation-tracking-with-a","title":"Video Instance Segmentation Tracking With a Modified VAE Architecture","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/visual-textual-capsule-routing-for-text-based","slug":"visual-textual-capsule-routing-for-text-based","title":"Visual-Textual Capsule Routing for Text-Based Video Segmentation","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-train-your-dragon-tamed-warping","title":"Tamed Warping Network for High-Resolution Semantic Video Segmentation","date":"2020-05-04","arxiv_id":"2005.01344","repositories_listed":0,"syntology":null},{"url":null,"slug":"lsm-learning-subspace-minimization-for-low","title":"LSM: Learning Subspace Minimization for Low-level Vision","date":"2020-04-20","arxiv_id":"2004.09197","repositories_listed":0,"syntology":null},{"url":null,"slug":"fair-latency-aware-metric-for-real-time-video","title":"Real-Time Segmentation Networks should be Latency Aware","date":"2020-04-06","arxiv_id":"2004.02574","repositories_listed":0,"syntology":null},{"url":"/paper/context-modulated-dynamic-networks-for-actor","slug":"context-modulated-dynamic-networks-for-actor","title":"Context Modulated Dynamic Networks for Actor and Action Video Segmentation with Language Queries","date":"2020-04-03","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coronary-artery-segmentation-in-angiographic","title":"Coronary Artery Segmentation in Angiographic Videos Using A 3D-2D CE-Net","date":"2020-03-26","arxiv_id":"2003.11851","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-temporal-video-segmentation-as","title":"Unsupervised Temporal Video Segmentation as an Auxiliary Task for Predicting the Remaining Surgery Duration","date":"2020-02-26","arxiv_id":"2002.11367","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-video-semantic-segmentation-with","title":"Efficient Video Semantic Segmentation with Labels Propagation and Refinement","date":"2019-12-26","arxiv_id":"1912.11844","repositories_listed":0,"syntology":null},{"url":null,"slug":"symmetric-block-low-rank-layers-for-fully","title":"Symmetric block-low-rank layers for fully reversible multilevel neural networks","date":"2019-12-14","arxiv_id":"1912.12137","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-video-object-segmentation-via","title":"Automatic Video Object Segmentation via Motion-Appearance-Stream Fusion and Instance-aware Segmentation","date":"2019-12-03","arxiv_id":"1912.01373","repositories_listed":0,"syntology":null},{"url":null,"slug":"every-frame-counts-joint-learning-of-video","title":"Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow","date":"2019-11-28","arxiv_id":"1911.12739","repositories_listed":0,"syntology":null},{"url":null,"slug":"191013348","title":"Sequential image processing methods for improving semantic video segmentation algorithms","date":"2019-10-29","arxiv_id":"1910.13348","repositories_listed":0,"syntology":null},{"url":null,"slug":"segeqa-video-segmentation-based-visual","title":"SegEQA: Video Segmentation Based Visual Attention for Embodied Question Answering","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mining-minimal-map-segments-for-visual-place","title":"Mining Minimal Map-Segments for Visual Place Classifiers","date":"2019-09-15","arxiv_id":"1909.09594","repositories_listed":0,"syntology":null},{"url":null,"slug":"msu-net-multiscale-statistical-u-net-for-real","title":"MSU-Net: Multiscale Statistical U-Net for Real-time 3D Cardiac MRI Video Segmentation","date":"2019-09-15","arxiv_id":"1909.06726","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-optimality-guarantees-for-nonconvex","title":"Global Optimality Guarantees for Nonconvex Unsupervised Video Segmentation","date":"2019-07-09","arxiv_id":"1907.04409","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-face-video-segmentation-via","title":"Dynamic Face Video Segmentation via Reinforcement Learning","date":"2019-07-02","arxiv_id":"1907.01296","repositories_listed":0,"syntology":null}],"record_sha256":"3d3579b6bb05fb62f4e4ac17eb752be63b889e5cb7e4406dfaf73ec97e0569ec","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}