学者档案2020-2026
Can Ma
University of Chinese Academy of Sciences
13论文数
2末位作者
24合作者人数
0一作
0独著
一作与末位作者按论文署名顺序统计,部分顶会采用姓氏字母顺序署名。
近期论文13
- Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training第 9 位,共 10 位作者CVPR 2026 · 9 次引用
- Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning第 8 位,共 10 位作者ICLR 2026 · 6 次引用
- MMTIT-Bench: A Multilingual and Multi-Scenario Benchmark with Cognition-Perception-Reasoning Guided Text-Image Machine Translation第 11 位,共 12 位作者CVPR 2026 · 6 次引用
- Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach第 4 位,共 5 位作者ICLR 2026 · 4 次引用
- SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs第 7 位,共 8 位作者NeurIPS 2025 · 5 次引用
- Gather and Trace: Rethinking Video TextVQA from an Instance-oriented Perspective第 7 位,共 8 位作者ACM MM 2025 · 2 次引用
- An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception Capability第 4 位,共 5 位作者ICML 2025
- Robust Multimodal Sentiment Analysis of Image-Text Pairs by Distribution-Based Feature Recovery and Fusion第 4 位,共 4 位作者ACM MM 2024 · 13 次引用
- Bridging Visual Affective Gap: Borrowing Textual Knowledge by Learning from Noisy Image-Text Pairs第 4 位,共 4 位作者ACM MM 2024 · 6 次引用
- Separate and Locate: Rethink the Text in Text-based Visual Question Answering第 4 位,共 5 位作者ACM MM 2023 · 18 次引用
- CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality第 5 位,共 9 位作者ACL 2023 · 2 次引用
- Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation第 2 位,共 4 位作者ACL 2021
- Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning第 5 位,共 7 位作者AAAI 2020 · 167 次引用
