Liang Li

20

Papers

102

Total Citations

Papers (20)

LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection

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

EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing

Online Video Understanding: OVBench and VideoChat-Online

Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation

Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing

Heterogeneous Prompt-Guided Entity Inferring and Distilling for Scene-Text Aware Cross-Modal Retrieval

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

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

Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning

WHALE-FL: Wireless and Heterogeneity Aware Latency Efficient Federated Learning over Mobile Devices via Adaptive Subnetwork Scheduling

Norm Tweaking: High-Performance Low-Bit Quantization of Large Language Models

SynSP: Synergy of Smoothness and Precision in Pose Sequences Refinement

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

DCTMamba: Advancing JPEG Image Restoration Through Long-Sequence Modeling and Adaptive Frequency Strategy

Tracking Tiny Drones against Clutter: Large-Scale Infrared Benchmark with Motion-Centric Adaptive Algorithm

Debiased Teacher for Day-to-Night Domain Adaptive Object Detection

Region-aware Difference Distilling with Attribute-guided Contrastive Regularization for Change Captioning

Union Is Strength! Unite the Power of LLMs and MLLMs for Chart Question Answering

Frequency Dynamic Convolution for Dense Image Prediction