Picture for Hongliang Li

Hongliang Li

HiHa: Introducing Hierarchical Harmonic Decomposition to Implicit Neural Compression for Atmospheric Data

Add code
Nov 09, 2024
Viaarxiv icon

ARIC: An Activity Recognition Dataset in Classroom Surveillance Images

Add code
Oct 16, 2024
Figure 1 for ARIC: An Activity Recognition Dataset in Classroom Surveillance Images
Figure 2 for ARIC: An Activity Recognition Dataset in Classroom Surveillance Images
Figure 3 for ARIC: An Activity Recognition Dataset in Classroom Surveillance Images
Figure 4 for ARIC: An Activity Recognition Dataset in Classroom Surveillance Images
Viaarxiv icon

Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation

Add code
Oct 02, 2024
Figure 1 for Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation
Figure 2 for Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation
Figure 3 for Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation
Figure 4 for Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation
Viaarxiv icon

Few-Shot Continual Learning for Activity Recognition in Classroom Surveillance Images

Add code
Sep 05, 2024
Viaarxiv icon

DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document Understanding

Add code
Aug 27, 2024
Figure 1 for DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document Understanding
Figure 2 for DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document Understanding
Figure 3 for DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document Understanding
Figure 4 for DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document Understanding
Viaarxiv icon

Distribution-Level Memory Recall for Continual Learning: Preserving Knowledge and Avoiding Confusion

Add code
Aug 04, 2024
Viaarxiv icon

No Re-Train, More Gain: Upgrading Backbones with Diffusion Model for Few-Shot Segmentation

Add code
Jul 23, 2024
Viaarxiv icon

On the Adversarial Robustness of Learning-based Image Compression Against Rate-Distortion Attacks

Add code
May 13, 2024
Figure 1 for On the Adversarial Robustness of Learning-based Image Compression Against Rate-Distortion Attacks
Figure 2 for On the Adversarial Robustness of Learning-based Image Compression Against Rate-Distortion Attacks
Figure 3 for On the Adversarial Robustness of Learning-based Image Compression Against Rate-Distortion Attacks
Figure 4 for On the Adversarial Robustness of Learning-based Image Compression Against Rate-Distortion Attacks
Viaarxiv icon

Bridging the Gap Between End-to-End and Two-Step Text Spotting

Add code
Apr 06, 2024
Viaarxiv icon

Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning

Add code
Apr 01, 2024
Viaarxiv icon