1

Toward an end-to-end implicit addressee modeling for dialogue disentanglement

iDAT: inverse Distillation Adapter-Tuning

Toward an end-to-end implicit addressee modeling for dialogue disentanglement

Learning to Floorplan like Human Experts via Reinforcement Learning

Ege-unet: an efficient group enhanced unet for skin lesion segmentation

LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live Streaming

Open-domain dialogue systems have made promising progress in recent years. While the state-of-the-art dialogue agents are built upon large-scale text-based social media data and large pre-trained models, there is no guarantee these agents could also …

DynaSlim: Dynamic Slimming for Vision Transformers

AV-TAD: Audio-Visual Temporal Action Detection with Transformer

CC-PoseNet: Towards human pose estimation in crowded classrooms

MALUNet: A Multi-Attention and Light-weight UNet for Skin Lesion Segmentation

Recently, some pioneering works have preferred applying more complex modules to improve segmentation performances. However, it is not friendly for actual clinical environments due to limited computing resources. To address this challenge, we propose …