45 skills found · Page 1 of 2
doc-doc / NExT QANExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR'21)
jayleicn / TVQA[EMNLP 2018] PyTorch code for TVQA: Localized, Compositional Video Question Answering
antoyang / FrozenBiLM[NeurIPS 2022] Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
thaolmk54 / Hcrn VideoqaImplementation for the paper "Hierarchical Conditional Relation Networks for Video Question Answering" (Le et al., CVPR 2020, Oral)
antoyang / Just Ask[ICCV 2021 Oral + TPAMI] Just Ask: Learning to Answer Questions from Millions of Narrated Videos
VRU-NExT / VideoQANo description available
MILVLG / Activitynet QaAn VideoQA dataset based on the videos from ActivityNet
doc-doc / NExT GQACan I Trust Your Answer? Visually Grounded Video Question Answering (CVPR'24, Highlight)
fanchenyou / HME VideoQAHeterogeneous Memory Enhanced Multimodal Attention Model for VideoQA
sail-sg / VGTVideo Graph Transformer for Video Question Answering (ECCV'22)
zhousheng97 / EgoTextVQA[CVPR'25] 🌟🌟 EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering
doc-doc / HQGAVideo as Conditional Graph Hierarchy for Multi-Granular Question Answering (AAAI'22, Oral)
hyounghk / VideoQADenseCapFrameGate ACL2020Code for ACL 2020 paper "Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA." Hyounghun Kim, Zineng Tang, Mohit Bansal.
qirui-chen / MultiHop EgoQA[AAAI 2025] Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos
TraffiX-VideoQA / TraffiX Qwen[ICML 2025] Official implementation of TraffiX-Qwen model introduced in TUMTraf VideoQA benchmark for roadside traffic video understanding.
yandex-datasphere / VideoQABotМастер-класс по созданию диалогового чат-бота на основе Retrieval-Augmented Generation
doc-doc / NExT OENExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR'21)
yl3800 / IGVThis repo contains code for Invariant Grounding for Video Question Answering
ZJULearning / VideoqaUnifying the Video and Question Attentions for Open-Ended Video Question Answering
noagarcia / ROLL VideoQAPyTorch code for ROLL, a knowledge-based video story question answering model.