Lune

Profiles2023-2025

Xize Cheng

Zhejiang University

11Papers
0Last author
11Unique co-authors
4First author
0Solo

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

Recent papers11

  1. OmniSep: Unified Omni-Modality Sound Separation with Query-MixupAuthor 1 of 11ICLR 2025
  2. VoxDialogue: Can Spoken Dialogue Systems Understand Information Beyond Words?Author 1 of 11ICLR 2025
  3. SegTalker: Segmentation-based Talking Face Generation with Mask-guided Local EditingAuthor 2 of 11ACM MM 2024 · 10 citations
  4. TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head TranslationAuthor 1 of 10ACL Findings 2024 · 9 citations
  5. Uni-Dubbing: Zero-Shot Speech Synthesis from Visual ArticulationAuthor 2 of 10ACL 2024 · 1 citation
  6. MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and RecognitionAuthor 1 of 10ICCV 2023 · 30 citations
  7. Exploring Group Video Captioning with Efficient Relational ApproximationAuthor 6 of 7ICCV 2023 · 17 citations
  8. TAVT: Towards Transferable Audio-Visual Text GenerationAuthor 6 of 7ACL 2023 · 9 citations
  9. Weakly-Supervised Spoken Video Grounding via Semantic Interaction LearningAuthor 6 of 7ACL 2023 · 7 citations
  10. Semantic-conditioned Dual Adaptation for Cross-domain Query-based Visual SegmentationAuthor 4 of 6ACL Findings 2023 · 5 citations
  11. Contrastive Token-Wise Meta-Learning for Unseen Performer Visual Temporal-Aligned TranslationAuthor 3 of 7ACL Findings 2023 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines