Papers with Code 아카이브
Video Question Answering
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 28
- 보존된 평가 기록
- 254
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/riflezhang/llava-hound-dpo
공식 코드Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward
https://github.com/rikeilong/bay-cat
공식 코드CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios
https://github.com/robinzixuan/Video-Question-Answering-HRI
공식 코드Open-Ended Multi-Modal Relational Reasoning for Video Question Answering
https://github.com/rupertluo/valley
공식 코드Valley: Video Assistant with Large Language model Enhanced abilitY
https://github.com/sail-sg/vgt
공식 코드https://github.com/salesforce/lavis
공식 코드https://github.com/sergeantchris/macx-socialiq
공식 코드Extending Compositional Attention Networks for Social Reasoning in Videos
https://github.com/shajiayu1/OmniDataComposer
공식 코드OmniDataComposer: A Unified Data Structure for Multimodal Data Fusion and Infinite Data Generation
https://github.com/shinying/dest
공식 코드https://github.com/showlab/all-in-one
공식 코드https://github.com/showlab/demovlp
공식 코드Revitalize Region Feature for Democratizing Video-Language Pre-training of Retrieval
https://github.com/showlab/mist
공식 코드MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering
https://github.com/showlab/movieseq
공식 코드https://github.com/sighingsnow/vf-eval
공식 코드VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos
https://github.com/snumprlab/SRT
공식 코드ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO
https://github.com/snumprlab/isr-dpo
공식 코드ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO
https://github.com/stanlei52/aqvsr
공식 코드AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant
https://github.com/stanlei52/tqvsr
공식 코드AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant
https://github.com/sts-vlcc/sts-vlcc
공식 코드https://github.com/subho406/OmniNet
공식 코드OmniNet: A unified architecture for multi-modal multi-task learning
https://github.com/t-montes/viqagent
공식 코드ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation
https://github.com/thanhnguyentang/neural-offline-rl
공식 코드VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation
https://github.com/thaolmk54/hcrn-videoqa
공식 코드Hierarchical Conditional Relation Networks for Video Question Answering
https://github.com/the-anonymous-bs/favor
공식 코드Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models
https://github.com/tingyu215/ts-llava
공식 코드https://github.com/traveler-framework/traveler
공식 코드TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering
https://github.com/trunpm/pmt-aaai23
공식 코드Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer
https://github.com/trunpm/tpt-for-videoqa
공식 코드Temporal Pyramid Transformer with Multimodal Interaction for Video Question Answering
https://github.com/tsujuifu/pytorch_empirical-mvm
공식 코드An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling
https://github.com/tsujuifu/pytorch_violet
공식 코드VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling
https://github.com/txh-mercury/cosa
공식 코드COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
https://github.com/txh-mercury/vast
공식 코드VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
https://github.com/tychen-sjtu/implicit-videoqa
공식 코드Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning
https://github.com/vision-cair/minigpt-4
공식 코드MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
https://github.com/vru-next/videoqa
공식 코드Video Question Answering: Datasets, Algorithms and Challenges
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.