Qingming Huang

27

Papers

80

Total Citations

Papers (27)

R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation

EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing

Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video

When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learning

Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs

Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification

LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders

NeurIPS 2025arXiv

Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning

Separation of Powers: On Segregating Knowledge from Observation in LLM-enabled Knowledge-based Visual Question Answering

VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set

NeurIPS 2025arXiv

Video Language Model Pretraining with Spatio-temporal Masking

Exploring Structural Degradation in Dense Representations for Self-supervised Learning

Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition

Data-free Neural Representation Compression with Riemannian Neural Dynamics

Modeling Language Tokens as Functionals of Semantic Fields

Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification

Relieving the Over-Aggregating Effect in Graph Transformers

Dis²Booth: Learning Image Distribution with Disentangled Features for Text-to-Image Diffusion Models

Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification

SSE-SAM: Balancing Head and Tail Classes Gradually Through Stage-Wise SAM

Image-to-video Adaptation with Outlier Modeling and Robust Self-learning

2243 ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection

Weakly Supervised Video Individual Counting

Prompt-Enhanced Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

ReconBoost: Boosting Can Achieve Modality Reconcilement

ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection