Lune

Profiles2021-2025

Junbin Xiao

National University of Singapore

13Papers
0Last author
14Unique co-authors
3First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers13

  1. Question-Answering Dense Video EventsAuthor 2 of 3SIGIR 2025 · 5 citations
  2. Visual Intention Grounding for Egocentric AssistantsAuthor 2 of 7ICCV 2025 · 2 citations
  3. EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question AnsweringAuthor 2 of 9CVPR 2025
  4. On the Consistency of Video Large Language Models in Temporal ComprehensionAuthor 2 of 4CVPR 2025
  5. Can I Trust Your Answer? Visually Grounded Video Question AnsweringAuthor 1 of 4CVPR 2024 · 44 citations
  6. LASO: Language-Guided Affordance Segmentation on 3D ObjectAuthor 3 of 7CVPR 2024
  7. Discovering Spatio-Temporal Rationales for Video Question AnsweringAuthor 2 of 5ICCV 2023 · 26 citations
  8. Video as Conditional Graph Hierarchy for Multi-Granular Question AnsweringAuthor 1 of 6AAAI 2022 · 145 citations
  9. Invariant Grounding for Video Question AnsweringAuthor 3 of 5CVPR 2022 · 108 citations
  10. Video Question Answering: Datasets, Algorithms and ChallengesAuthor 2 of 6EMNLP 2022 · 70 citations
  11. Equivariant and Invariant Grounding for Video Question AnsweringAuthor 3 of 4ACM MM 2022 · 33 citations
  12. Video Visual Relation Detection via Iterative InferenceAuthor 2 of 3ACM MM 2021 · 41 citations
  13. NExT-QA: Next Phase of Question-Answering to Explaining Temporal ActionsAuthor 1 of 4CVPR 2021
Dusk over the sea between two cliffs drawn in fine vertical lines