157 citations · 510 across the 21 of their papers we have counts for
22 papers
MobileViCLIP: An Efficient Video-Text Model for Mobile Devices
Min Yang, Zihan Jia, Zhilin Dai +2
Efficient lightweight neural networks are with increasing attention due to their faster reasoning speed and easier deployment on mobile devices. However, existing video pre-trained…
StageInteractor: Query-based Object Detector with Cross-stage Interaction
Yao Teng, Haisong Liu, Sheng Guo +1
Previous object detectors make predictions based on dense grid points or numerous preset anchors. Most of these detectors are trained with one-to-many label assignment strategies.…
PDPP: Projected Diffusion for Procedure Planning in Instructional Videos
Hanlin Wang, Yilu Wu, Sheng Guo +1
In this paper, we study the problem of procedure planning in instructional videos, which aims to make a plan (i.e. a sequence of actions) given the current visual observation and t…
CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets
Jiange Yang, Sheng Guo, Gangshan Wu +1
Current RGB-D scene recognition approaches often train two standalone backbones for RGB and depth modalities with the same Places or ImageNet pre-training. However, the pre-trained…
Cross-Architecture Self-supervised Video Representation Learning
Sheng Guo, Zihua Xiong, Yujie Zhong +4
In this paper, we present a new cross-architecture contrastive learning (CACL) framework for self-supervised video representation learning. CACL consists of a 3D CNN and a video tr…
AdaMixer: A Fast-Converging Query-Based Object Detector
Ziteng Gao, Limin Wang, Bing Han +1
Traditional object detectors employ the dense paradigm of scanning over locations and scales in an image. The recent query-based object detectors break this convention by decoding…
InsCLR: Improving Instance Retrieval with Self-Supervision
Zelu Deng, Yujie Zhong, Sheng Guo +1
This work aims at improving instance retrieval with self-supervision. We find that fine-tuning using the recently developed self-supervised (SSL) learning methods, such as SimCLR a…
A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark
Zhenxi Zhu, Limin Wang, Sheng Guo +1
The existing few-shot video classification methods often employ a meta-learning paradigm by designing customized temporal alignment module for similarity calculation. While signifi…
Mutually-aware Sub-Graphs Differentiable Architecture Search
Haoxian Tan, Sheng Guo, Yujie Zhong +2
Differentiable architecture search is prevalent in the field of NAS because of its simplicity and efficiency, where two paradigms, multi-path algorithms and single-path methods, ar…
Unchain the Search Space with Hierarchical Differentiable Architecture Search
Guanting Liu, Yujie Zhong, Sheng Guo +2
Differentiable architecture search (DAS) has made great progress in searching for high-performance architectures with reduced computational cost. However, DAS-based methods mainly…
Representation Sharing for Fast Object Detector Search and Beyond
Yujie Zhong, Zelu Deng, Sheng Guo +2
Region Proposal Network (RPN) provides strong support for handling the scale variation of objects in two-stage object detection. For one-stage detectors which do not have RPN, it i…
Wavelet Integrated CNNs for Noise-Robust Image Classification
Qiufu Li, Linlin Shen, Sheng Guo +1
Convolutional Neural Networks (CNNs) are generally prone to noise interruptions, i.e., small image noise can cause drastic changes in the output. To suppress the noise effect to th…
Knowledge Integration Networks for Action Recognition
Shiwen Zhang, Sheng Guo, Limin Wang +2
In this work, we propose Knowledge Integration Networks (referred as KINet) for video action recognition. KINet is capable of aggregating meaningful context features which are of g…
V4D:4D Convolutional Neural Networks for Video-level Representation Learning
Shiwen Zhang, Sheng Guo, Weilin Huang +2
Most existing 3D CNNs for video representation learning are clip-based methods, and thus do not consider video-level temporal evolution of spatio-temporal features. In this paper,…
Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation
Weifeng Ge, Sheng Guo, Weilin Huang +1
Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only. Unlike previous methods which are composed of multiple…
The iMaterialist Fashion Attribute Dataset
Sheng Guo, Weilin Huang, Xiao Zhang +6
Large-scale image databases such as ImageNet have significantly advanced image classification and other visual recognition tasks. However much of these datasets are constructed onl…
CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
Sheng Guo, Weilin Huang, Haozhi Zhang +4
We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled raw from the Internet by using te…
Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs
Limin Wang, Sheng Guo, Weilin Huang +2
Convolutional Neural Networks (CNNs) have made remarkable progress on scene recognition, partially due to these recent large-scale scene datasets, such as the Places and Places2. S…
Locally-Supervised Deep Hybrid Model for Scene Recognition
Sheng Guo, Weilin Huang, Limin Wang +1
Convolutional neural networks (CNN) have recently achieved remarkable successes in various image classification and understanding tasks. The deep features obtained at the top fully…
Better Exploiting OS-CNNs for Better Event Recognition in Images
Limin Wang, Zhe Wang, Sheng Guo +1
Event recognition from still images is one of the most important problems for image understanding. However, compared with object recognition and scene recognition, event recognitio…
Places205-VGGNet Models for Scene Recognition
Limin Wang, Sheng Guo, Weilin Huang +1
VGGNets have turned out to be effective for object recognition in still images. However, it is unable to yield good performance by directly adapting the VGGNet models trained on th…
Local Color Contrastive Descriptor for Image Classification
Sheng Guo, Weilin Huang, Yu Qiao
Image representation and classification are two fundamental tasks towards multimedia content retrieval and understanding. The idea that shape and texture information (e.g. edge or…