https://github.com/tfzhou/MATNet
공식 코드Motion-Attentive Transition for Zero-Shot Video Object Segmentation
Papers with Code 아카이브
Scene Understanding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 6
- 평가표
- 3
- 보존된 평가 기록
- 5
Scene understanding involves interpreting the visual information of a scene, including objects, their spatial relationships, and the overall layout. It goes beyond simple object recognition by considering the context and how objects relate to each other and the environment.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/tfzhou/vs-survey
공식 코드https://github.com/the-ai-alliance/geo-bench-vlm
공식 코드GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks
https://github.com/theevann/fast-cwm-segmentation
공식 코드Borrowing from yourself: Faster future video segmentation with partial channel update
https://github.com/threedworld-mit/tdw
공식 코드ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation
https://github.com/thu-lyj-lab/ar-seg
공식 코드Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos
https://github.com/thunlp/pevl
공식 코드PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models
https://github.com/thusiyuan/cooperative_scene_parsing
공식 코드Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation
https://github.com/tianfu18/diff-feats-pose
공식 코드Object Pose Estimation via the Aggregation of Diffusion Features
https://github.com/tien-d/EgoDepthNormal
공식 코드Egocentric Scene Understanding via Multimodal Spatial Rectifier
https://github.com/tobran/galip
공식 코드GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis
https://github.com/tong-zeng/dvbench
공식 코드https://github.com/tri-ml/prismatic-vlms
공식 코드Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
https://github.com/tri-ml/vedet
공식 코드https://github.com/tri-ml/vlm-evaluation
공식 코드Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
https://github.com/triumph123aaa/grid-augmented-vision
공식 코드https://github.com/tsinghua-mars-lab/trackocc
공식 코드https://github.com/tsunghan-wu/redal
공식 코드ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation
https://github.com/tue-mps/panoptic_parts
공식 코드Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene Understanding
https://github.com/tue-mps/road-as-graph
공식 코드Self-Supervised Road Layout Parsing with Graph Auto-Encoding
https://github.com/tui-nicr/emsanet
공식 코드Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments
https://github.com/tui-nicr/panoptic-mapping
공식 코드https://github.com/tum-vision/scenedino
공식 코드Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
https://github.com/tyroneli/cua_o3d
공식 코드Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding
https://github.com/uark-cviu/fredom
공식 코드FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
https://github.com/ucr-robotics/citrus-farm-dataset
공식 코드Multimodal Dataset for Localization, Mapping and Crop Monitoring in Citrus Tree Farms
https://github.com/ufukertenli/streamdeq-code
공식 코드https://github.com/umdatasciencelab/personalized_pca
공식 코드https://github.com/uml-marine-robotics/massmind
공식 코드https://github.com/uncbiag/livos
공식 코드LiVOS: Light Video Object Segmentation with Gated Linear Matching
https://github.com/unique1i/scenesplat
공식 코드SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining
https://github.com/unmannedlab/RELLIS-3D
공식 코드https://github.com/ustczhouyu/contour
공식 코드https://github.com/ut-vision/actionvos
공식 코드https://github.com/uva-dsa/runtime_robscene_seg_2context
공식 코드Robotic Scene Segmentation with Memory Network for Runtime Surgical Context Inference
https://github.com/uverma/ManipalUAVid
공식 코드UVid-Net: Enhanced Semantic Segmentation of UAV Aerial Videos by Embedding Temporal Information
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.