https://github.com/hcplab-sysu/cmcir
공식 코드Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering
Papers with Code 아카이브
Relational Reasoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 1
The goal of Relational Reasoning is to figure out the relationships among different entities, such as image pixels, words or sentences, human skeletons or interactive moving agents.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/hkuds/hgcl
공식 코드https://github.com/hoanganhpham1006/cost
공식 코드Video Dialog as Conversation about Objects Living in Space-Time
https://github.com/hongluzhou/composer
공식 코드COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality
https://github.com/hxiaoyang/lm-raven
공식 코드In-Context Analogical Reasoning with Pre-Trained Language Models
https://github.com/ibayer/PAKDD2015
공식 코드Graph Based Relational Features for Collective Classification
https://github.com/ideas-laboratory/graphical-perception
공식 코드Generalization of CNNs on Relational Reasoning with Bar Charts
https://github.com/ivanDonadello/Visual-Relationship-Detection-LTN
공식 코드Compensating Supervision Incompleteness with Prior Knowledge in Semantic Image Interpretation
https://github.com/jacobyuan7/rlipv2
공식 코드RLIPv2: Fast Scaling of Relational Language-Image Pre-training
https://github.com/jonathanfeldstein/prism
공식 코드Principled and Efficient Motif Finding for Structure Learning of Lifted Graphical Models
https://github.com/jyhong0304/SII
공식 코드https://github.com/jyhong0304/visual-relationship-detection-rwfn
공식 코드https://github.com/jylins/core-text
공식 코드CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning
https://github.com/kkteru/grail
공식 코드https://github.com/koustuvsinha/clutrr
공식 코드Compositional Language Understanding with Text-based Relational Reasoning
https://github.com/kuanglab/LowrankTLP
공식 코드Scalable Label Propagation for Multi-relational Learning on the Tensor Product of Graphs
https://github.com/lalithjets/global-reasoned-multi-task-model
공식 코드Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding
https://github.com/lamm-mit/graph-aware-transformers
공식 코드Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers
https://github.com/logictensornetworks/logictensornetworks
공식 코드https://github.com/luisrui/Multimodal-Relation-Extrapolation
공식 코드Zero-Shot Relational Learning for Multimodal Knowledge Graphs
https://github.com/lulor/ood-class-separation
공식 코드Large Class Separation is not what you need for Relational Reasoning-based OOD Detection
https://github.com/lytang63/OCRT
공식 코드OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad
https://github.com/mauriciolp/inter-rel-net
공식 코드Interaction Relational Network for Mutual Action Recognition
https://github.com/mdda/relationships-from-entity-stream
공식 코드https://github.com/mediabrain-sjtu/groupnet
공식 코드GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning
https://github.com/microsoft/DEKCOR-CommonsenseQA
공식 코드Fusing Context Into Knowledge Graph for Commonsense Question Answering
https://github.com/ml-research/pix2code
공식 코드Pix2Code: Learning to Compose Neural Visual Concepts as Programs
https://github.com/mmejri3/resolve
공식 코드https://github.com/mpatacchiola/self-supervised-relational-reasoning
공식 코드Self-Supervised Relational Reasoning for Representation Learning
https://github.com/namkyeong/cgib
공식 코드Conditional Graph Information Bottleneck for Molecular Relational Learning
https://github.com/namkyeong/cmrl
공식 코드Shift-Robust Molecular Relational Learning with Causal Substructure
https://github.com/nanguoshun/LSR
공식 코드Reasoning with Latent Structure Refinement for Document-Level Relation Extraction
https://github.com/ngl567/GANA-FewShotKGC
공식 코드https://github.com/nhiratani/quadratic_binding
공식 코드Optimal quadratic binding for relational reasoning in vector symbolic neural architectures
https://github.com/nkatzz/OLED
공식 코드Semi-Supervised Online Structure Learning for Composite Event Recognition
https://github.com/onmyoji-xiao/3dvg_secg
공식 코드SeCG: Semantic-Enhanced 3D Visual Grounding via Cross-modal Graph Attention
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.