Papers with Code 아카이브
Video Semantic Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 5
- 보존된 평가 기록
- 26
The goal of video semantic segmentation is to assign a predefined class to each pixel in all frames of a video. This requires the model not only to predict accurate segmentation masks but also to ensure that these masks remain temporally consistent across frames. This task has broad applications in areas such as autonomous driving, medical video analysis, and AR/VR.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/lxa9867/R2VOS
공식 코드Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus
https://github.com/lxtgh/omg-seg
공식 코드https://github.com/lxtgh/tube-link
공식 코드Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation
https://github.com/lxtgh/video-k-net
공식 코드Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation
https://github.com/lyxok1/STM-Training
공식 코드Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation
https://github.com/magic-research/Sa2VA
공식 코드Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
https://github.com/magnus-haw/arcjetcv
공식 코드arcjetCV: an open-source software to analyze material ablation
https://github.com/maoyunyao/joint
공식 코드Joint Inductive and Transductive Learning for Video Object Segmentation
https://github.com/mark12ding/sam2long
공식 코드SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
https://github.com/mattpfr/lmanet
공식 코드https://github.com/max810/XMem2
공식 코드XMem++: Production-level Video Segmentation From Few Annotated Frames
https://github.com/mazurowski-lab/SlicerSegmentHumanBody
공식 코드Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2
https://github.com/mazurowski-lab/slm-sam2
공식 코드Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2
https://github.com/mbzuai-oryx/videomolmo
공식 코드https://github.com/mcahny/vps
공식 코드https://github.com/medaitech/rab
공식 코드https://github.com/medaitech/tcmn
공식 코드One-Shot Medical Video Object Segmentation via Temporal Contrastive Memory Networks
https://github.com/menglcool/segic
공식 코드SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation
https://github.com/mhashas/Exploiting-Temporality-For-Semi-Supervised-Video-Segmentation
공식 코드Exploiting Temporality for Semi-Supervised Video Segmentation
https://github.com/microsoft/transductive-vos.pytorch
공식 코드https://github.com/minghanli/univs
공식 코드UniVS: Unified and Universal Video Segmentation with Prompts as Queries
https://github.com/minhoooo1/catmae
공식 코드Concatenated Masked Autoencoders as Spatial-Temporal Learner
https://github.com/mkg1204/rhmnet-for-ssvos
공식 코드Reliability-Hierarchical Memory Network for Scribble-Supervised Video Object Segmentation
https://github.com/mlvlab/vidchain
공식 코드VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
https://github.com/modelstreaming/ams
공식 코드Real-Time Video Inference on Edge Devices via Adaptive Model Streaming
https://github.com/motern88/det-sam2
공식 코드https://github.com/msiam/mmc-multiscalememory
공식 코드Multiscale Memory Comparator Transformer for Few-Shot Video Segmentation
https://github.com/msiam/tti_fsvos
공식 코드Temporal Transductive Inference for Few-Shot Video Object Segmentation
https://github.com/msracver/Deep-Feature-Flow
공식 코드https://github.com/mtec-tuhh/polypnextlstm
공식 코드PolypNextLSTM: A lightweight and fast polyp video segmentation network using ConvNext and ConvLSTM
https://github.com/mttr2021/MTTR
공식 코드End-to-End Referring Video Object Segmentation with Multimodal Transformers
https://github.com/multimediafor/truvil
공식 코드Trusted Video Inpainting Localization via Deep Attentive Noise Learning
https://github.com/multimediafor/vilocal
공식 코드https://github.com/nankepan/VIPMT
공식 코드Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation
https://github.com/nust-machine-intelligence-laboratory/hcpn
공식 코드Co-attention Propagation Network for Zero-Shot Video Object Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.