paper-with-me

Papers

Hypergraph Transformer: Weakly-supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering

2022-04-22 · ACL 2022 5 · Yu-Jung Heo, Eun-Sol Kim, Woo Suk Choi, Byoung-Tak Zhang

Knowledge-based visual question answering (QA) aims to answer a question which requires visually-grounded external knowledge beyond image content itself. Answering complex questions that require multi-hop reasoning under weak supervision is considered as a challenging problem since i) no supervision is given to the reasoning process and ii) high-order semantics of multi-hop knowledge facts need to be captured. In this paper, we introduce a concept of hypergraph to encode high-level semantics of a question and a knowledge base, and to learn high-order associations between them. The proposed model, Hypergraph Transformer, constructs a question hypergraph and a query-aware knowledge hypergraph, and infers an answer by encoding inter-associations between two hypergraphs and intra-associations in both hypergraph itself. Extensive experiments on two knowledge-based visual QA and two knowledge-based textual QA demonstrate the effectiveness of our method, especially for multi-hop reasoning problem. Our source code is available at https://github.com/yujungheo/kbvqa-public.

📄 PDF Abstract BibTeX arXiv:2204.10448

Code (1)

yujungheo/kbvqa-public 공식 구현 pytorch

Tasks

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Reasoning Mamba: Hypergraph-Guided Region Relation Calculating for Weakly Supervised Affordance Grounding

2025-01-01 · CVPR 2025 1 · Yuxuan Wang, Aming Wu, Muli Yang, Yukuan Min 외

This paper pays attention to Weakly Supervised Affordance Grounding (WSAG) task that aims to train model to identify affordance regions using human-object interaction images and egocentric images without the need for…

Human-Object Interaction DetectionMambaRelation

Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers

2025-01-18 · Xiaoyu Li, YIngyu Liang, Jiangxuan Long, Zhenmei Shi 외

Looped Transformers have shown exceptional neural algorithmic reasoning capability in simulating traditional graph algorithms, but their application to more complex structures like hypergraphs remains underexplored. Hype…

Combinatorial Optimization

Hypergraph Convolutional Networks for Weakly-Supervised Semantic Segmentation

2022-10-11 · Jhony H. Giraldo, Vincenzo Scarrica, Antonino Staiano, Francesco Camastra 외

Semantic segmentation is a fundamental topic in computer vision. Several deep learning methods have been proposed for semantic segmentation with outstanding results. However, these models require a lot of densely annotat…

SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition

2024-11-08 · Abhisek Ray, Ayush Raj, Maheshkumar H. Kolekar

Extracting multiscale contextual information and higher-order correlations among skeleton sequences using Graph Convolutional Networks (GCNs) alone is inadequate for effective action classification. Hypergraph convolutio…

Action ClassificationActivity Recognition

Hyper-STTN: Social Group-aware Spatial-Temporal Transformer Network for Human Trajectory Prediction with Hypergraph Reasoning

2024-01-12 · Weizheng Wang, Chaowei Wang, Baijian Yang, Guohua Chen 외

Predicting crowded intents and trajectories is crucial in varouls real-world applications, including service robots and autonomous vehicles. Understanding environmental dynamics is challenging, not only due to the comple…

Autonomous VehiclesTrajectory Prediction