research
∙
08/17/2023
Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling
To bridge the physical and virtual worlds for rapidly developed VR/AR ap...
share
research
∙
06/15/2023
COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
Due to the limited scale and quality of video-text training corpus, most...
research
∙
05/24/2023
Delving Deeper into Data Scaling in Masked Image Modeling
Understanding whether self-supervised learning methods can scale with un...
research
∙
05/22/2023
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending
Large-scale image-text contrastive pre-training models, such as CLIP, ha...
research
∙
01/19/2023
Multimodal Video Adapter for Parameter Efficient Video Text Retrieval
State-of-the-art video-text retrieval (VTR) methods usually fully fine-t...
research
∙
01/18/2023
Temporal Perceiving Video-Language Pre-training
Video-Language Pre-training models have recently significantly improved ...
research
∙
01/15/2023
CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition
Contrastive Masked Autoencoder (CMAE), as a new self-supervised framewor...
research
∙
11/09/2022
NoiSER: Noise is All You Need for Enhancing Low-Light Images Without Task-Related Data
This paper is about an extraordinary phenomenon. Suppose we don't use an...
research
∙
11/04/2022
OSIC: A New One-Stage Image Captioner Coined
Mainstream image caption models are usually two-stage captioners, i.e., ...
research
∙
07/27/2022
Contrastive Masked Autoencoders are Stronger Vision Learners
Masked image modeling (MIM) has achieved promising results on various vi...
research
∙
07/27/2022
AutoTransition: Learning to Recommend Video Transition Effects
Video transition effects are widely used in video editing to connect sho...
research
∙
10/26/2021
Conflict-Averse Gradient Descent for Multi-task Learning
The goal of multi-task learning is to enable more efficient learning tha...
research
∙
04/27/2021
One Backward from Ten Forward, Subsampling for Large-Scale Deep Learning
Deep learning models in large-scale machine learning systems are often c...
research
∙
04/22/2021
Token Labeling: Training a 85.4 56M Parameters on ImageNet
This paper provides a strong baseline for vision transformers on the Ima...
research
∙
03/22/2021
DeepViT: Towards Deeper Vision Transformer
Vision transformers (ViTs) have been successfully applied in image class...
research
∙
03/22/2021
AutoSpace: Neural Architecture Search with Less Human Interference
Current neural architecture search (NAS) algorithms still require expert...
research
∙
11/10/2020
Human-centric Spatio-Temporal Video Grounding With Visual Transformers
In this work, we introduce a novel task - Humancentric Spatio-Temporal V...
research
∙
04/04/2020
Neural Architecture Search for Lightweight Non-Local Networks
Non-Local (NL) blocks have been widely studied in various vision tasks. ...
research
∙
12/30/2019
RC-DARTS: Resource Constrained Differentiable Architecture Search
Recent advances show that Neural Architectural Search (NAS) method is ab...
research
∙
12/20/2019
AtomNAS: Fine-Grained End-to-End Neural Architecture Search
Designing of search space is a critical problem for neural architecture ...
research
∙
07/12/2019
Deep Model Compression via Filter Auto-sampling
The recent WSNet [1] is a new model compression method through sampling ...
research
∙
11/28/2017
WSNet: Compact and Efficient Networks with Weight Sampling
We present a new approach and a novel architecture, termed WSNet, for le...
research
∙
11/09/2017
Predicting Scene Parsing and Motion Dynamics in the Future
The ability of predicting the future is important for intelligent system...
research
∙
07/06/2017
Dual Path Networks
In this work, we present a simple, highly efficient and modularized Dual...
research
∙
04/18/2017
Deep Self-Taught Learning for Weakly Supervised Object Localization
Most existing weakly supervised localization (WSL) approaches learn dete...
research
∙
03/08/2017
Tree-Structured Reinforcement Learning for Sequential Object Localization
Existing object proposal algorithms usually search for possible object r...
research
∙
01/24/2017
Training Group Orthogonal Neural Networks with Privileged Information
Learning rich and diverse representations is critical for the performanc...
research
∙
12/01/2016
Video Scene Parsing with Predictive Feature Learning
In this work, we address the challenging video scene parsing problem by ...
research
∙
08/27/2016
Multi-Path Feedback Recurrent Neural Network for Scene Parsing
In this paper, we consider the scene parsing problem and propose a novel...
research
∙
12/22/2015