Papers with Code 아카이브

Scene Understanding

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/declare-lab/emma-x

공식 코드

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning

https://github.com/deeplab-ai/selfsupervisedvrd

공식 코드

Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction

https://github.com/deepmind/threednel

공식 코드

3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimation

https://github.com/deeptag/cstm

공식 코드

Continuous Spatio-Temporal Memory Networks for 4D Cardiac Cine MRI Segmentation

https://github.com/deeptibhegde/clip-goes-3d

공식 코드

CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition

https://github.com/defaultrui/vln-ver

공식 코드

Volumetric Environment Representation for Vision-Language Navigation

https://github.com/delair-ai/DISCA

공식 코드

Interactive Learning for Semantic Segmentation in Earth Observation

https://github.com/denabazazian/SoftPHOC_TextDescriptor

공식 코드

Soft-PHOC Descriptor for End-to-End Word Spotting in Egocentric Scene Images

https://github.com/dengpingfan/csu

공식 코드

Advances in Deep Concealed Scene Understanding

https://github.com/dexianghong/manet

공식 코드

Multi-Attention Network for Compressed Video Referring Object Segmentation

https://github.com/dibschat/tempAgg

공식 코드

Temporal Aggregate Representations for Long-Range Video Understanding

https://github.com/dipika-singhania/C2F-TCN

공식 코드

Coarse to Fine Multi-Resolution Temporal Convolutional Network

https://github.com/djiajunustc/H-23D_R-CNN

공식 코드

From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection

https://github.com/dk-liang/uniseg3d

공식 코드

A Unified Framework for 3D Scene Understanding

https://github.com/dlut-yyc/isomer

공식 코드

Isomer: Isomerous Transformer for Zero-shot Video Object Segmentation

https://github.com/donglao/srt

공식 코드

Sub-token ViT Embedding via Stochastic Resonance Transformers

https://github.com/doubledaibo/drnet

공식 코드

Detecting Visual Relationships with Deep Relational Networks

https://github.com/dreichCSL/GQA_generalization_splits

공식 코드

Visually Grounded VQA by Lattice-based Retrieval

https://github.com/dtu-pas/rumexleaves-centernet

공식 코드

Zoom in on the Plant: Fine-grained Analysis of Leaf, Stem and Vein Instances

https://github.com/dukebw/SSTVOS

공식 코드

SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation

https://github.com/dut-csj/pvuw2023-vss-3rd

공식 코드

3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW

https://github.com/dvl-tum/e-osvos

공식 코드

Make One-Shot Video Object Segmentation Efficient Again

https://github.com/dvlab-research/groupcontrast

공식 코드

GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding

https://github.com/dvssajay/Ikshana-A-Theory-of-Human-Scene-Understanding-Mechanism

공식 코드

The Ikshana Hypothesis of Human Scene Understanding

https://github.com/dzh19990407/lbdt

공식 코드

Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation

https://github.com/eaphan/upidet

공식 코드

Unleash the Potential of Image Branch for Cross-modal 3D Object Detection

https://github.com/eceo-epfl/coralscapesScripts

공식 코드

The Coralscapes Dataset: Semantic Scene Understanding in Coral Reefs

https://github.com/ecker-lab/object-centric-representation-benchmark

공식 코드

Benchmarking Unsupervised Object Representations for Video Sequences

https://github.com/edbeeching/3d_control_deep_rl

공식 코드

Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer

https://github.com/ehsanik/SeGAN

공식 코드

SeGAN: Segmenting and Generating the Invisible

https://github.com/endlinc/llava-spacesgg

공식 코드

LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations

https://github.com/engzenia/wIoU

공식 코드

Weighted Intersection over Union (wIoU) for Evaluating Image Segmentation

https://github.com/envision-research/mtmamba

공식 코드

MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders

https://github.com/epic-kitchens/visor-hos

공식 코드

EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations

https://github.com/epic-kitchens/visor-vos

공식 코드

EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations

https://github.com/epic-kitchens/visor-wdtcf

공식 코드

EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.