https://github.com/tychen-sjtu/implicit-videoqa
공식 코드Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning
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/tyler-hayes/REMIND
공식 코드REMIND Your Neural Network to Prevent Catastrophic Forgetting
https://github.com/uber/ludwig
공식 코드https://github.com/ucsc-vlaa/vllm-safety-benchmark
공식 코드How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
https://github.com/uds-lsv/premise
공식 코드Label-Descriptive Patterns and Their Application to Characterizing Classification Errors
https://github.com/ukplab/acl2024-sparc-and-sparp
공식 코드https://github.com/ukplab/eacl2023-xlingvqa
공식 코드https://github.com/umd-huang-lab/sima
공식 코드Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement
https://github.com/uni-medical/GMAI-MMBench
공식 코드GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI
https://github.com/uni-medical/gmai-vl
공식 코드https://github.com/uni-medical/gmai-vl-r1
공식 코드GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning
https://github.com/uniadapter/uniadapter
공식 코드UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling
https://github.com/unimodal4reasoning/chartvlm
공식 코드StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding
https://github.com/unimodal4reasoning/simchart9k
공식 코드StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding
https://github.com/uniqzheng/hfr-bvqa
공식 코드FAVER: Blind Quality Prediction of Variable Frame Rate Videos
https://github.com/uolmm/tpqi-vqa
공식 코드Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessment
https://github.com/upper9527/gerea
공식 코드GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering
https://github.com/ustc-hyin/ClearSight
공식 코드https://github.com/usydnlp/REXUP
공식 코드https://github.com/uta-smile/TCL
공식 코드Vision-Language Pre-Training with Triple Contrastive Learning
https://github.com/vacancy/NSCL-PyTorch-Release
공식 코드https://github.com/vaidehi99/causalinfomin
공식 코드Debiasing Multimodal Models via Causal Information Minimization
https://github.com/vaidehi99/unlok-vqa
공식 코드Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
https://github.com/vaishwarya96/GroVE
공식 코드https://github.com/val-iisc/sketchguess
공식 코드Game of Sketches: Deep Recurrent Models of Pictionary-style Word Guessing
https://github.com/vanessadamario/understanding_reasoning
공식 코드How Modular Should Neural Module Networks Be for Systematic Generalization?
https://github.com/vanh17/techqa
공식 코드Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading
https://github.com/varunj/cvpr-vqe
공식 코드https://github.com/vectorinstitute/humanibench
공식 코드HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation
https://github.com/vedantpalit/towards-vision-language-mechanistic-interpretability
공식 코드Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP
https://github.com/venturamor/cultext-2-i
공식 코드Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models
https://github.com/vinceouti/citynavagent
공식 코드https://github.com/vipulgupta1011/swapmix
공식 코드https://github.com/vis-nlp/chartgemma
공식 코드ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild
https://github.com/vis-nlp/chartinstruct
공식 코드ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning
https://github.com/vis-nlp/chartqa
공식 코드ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.