Profiles2020-2026
Can Ma
University of Chinese Academy of Sciences
13Papers
2Last author
24Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers13
- Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware TrainingAuthor 9 of 10CVPR 2026 · 9 citations
- Echo: Towards Advanced Audio Comprehension via Audio-Interleaved ReasoningAuthor 8 of 10ICLR 2026 · 6 citations
- MMTIT-Bench: A Multilingual and Multi-Scenario Benchmark with Cognition-Perception-Reasoning Guided Text-Image Machine TranslationAuthor 11 of 12CVPR 2026 · 6 citations
- Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable ApproachAuthor 4 of 5ICLR 2026 · 4 citations
- SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed GraphsAuthor 7 of 8NeurIPS 2025 · 5 citations
- Gather and Trace: Rethinking Video TextVQA from an Instance-oriented PerspectiveAuthor 7 of 8ACM MM 2025 · 2 citations
- An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception CapabilityAuthor 4 of 5ICML 2025
- Robust Multimodal Sentiment Analysis of Image-Text Pairs by Distribution-Based Feature Recovery and FusionAuthor 4 of 4ACM MM 2024 · 13 citations
- Bridging Visual Affective Gap: Borrowing Textual Knowledge by Learning from Noisy Image-Text PairsAuthor 4 of 4ACM MM 2024 · 6 citations
- Separate and Locate: Rethink the Text in Text-based Visual Question AnsweringAuthor 4 of 5ACM MM 2023 · 18 citations
- CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High QualityAuthor 5 of 9ACL 2023 · 2 citations
- Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text GenerationAuthor 2 of 4ACL 2021
- Video Cloze Procedure for Self-Supervised Spatio-Temporal LearningAuthor 5 of 7AAAI 2020 · 167 citations
