https://github.com/zhayefei/off-topic-GCBiA
Gated Convolutional Bidirectional Attention-based Model for Off-topic Spoken Response Detection
Papers with Code 아카이브
Visual Question Answering (VQA)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 9
- 평가표
- 76
- 보존된 평가 기록
- 725
Visual Question Answering (VQA) is a task in computer vision that involves answering questions about an image. The goal of VQA is to teach machines to understand the content of an image and answer questions about it in natural language.
Image Source: visualqa.org
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/zhijie-group/r1-zero-vsi
https://github.com/zhixinlai/llmboostmedical
Frozen Transformers in Language Models Are Effective Visual Encoder Layers
https://github.com/zihanzhaosjtu/librisqa
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
https://github.com/zihaow123/unimm
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
https://github.com/zijieli-Jlee/Dual-Diffusion
Dual Diffusion for Unified Image Generation and Understanding
https://github.com/zilongzheng/visdial-gnn
Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
https://github.com/zirui-ray-liu/wtacrs
LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning
https://github.com/ziwei-zheng/nullu
Evaluating Object Hallucination in Large Vision-Language Models
https://github.com/zixuwang1996/VQA-reading-list
Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering
https://github.com/ziyan-xiaoyu/spatialmqa
https://github.com/zjukg/maco
Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey
https://github.com/zjukg/mygo
Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey
https://github.com/zjukg/snag
Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey
https://github.com/zli12321/qa_metrics
https://github.com/zli12321/videohallu
https://github.com/zrrskywalker/point-bind
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
https://github.com/zwx8981/tcsvt-2022-bvqa
Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception
https://github.com/zwxalgorithm/pythia
https://github.com/zxqcreations/faster-rcnn-tf
https://github.com/zyang1580/binllm
MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
https://gitlab.com/Percipiote/skelda
https://gitlab.com/birder/birder
Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
https://huggingface.co/BAAI/Aquila-VL-2B-llava-qwen
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data
https://huggingface.co/datasets/BAAI/Infinity-MM
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data
https://huggingface.co/datasets/Fangjun/RoomSpace
https://huggingface.co/datasets/WaltonFuture/InstructionGPT-4
InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4
https://huggingface.co/datasets/jjjjh/MM-Instruct
MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment
https://huggingface.co/spaces/daeron/CONVS2S-EVJVQA-DEMO
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.