research
∙
12/03/2022
Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution
In contrast to fully supervised methods using pixel-wise mask labels, bo...
share
research
∙
07/19/2022
Box-supervised Instance Segmentation with Level Set Evolution
In contrast to the fully supervised methods using pixel-wise mask labels...
research
∙
06/15/2022
SP-ViT: Learning 2D Spatial Priors for Vision Transformers
Recently, transformers have shown great potential in image classificatio...
research
∙
04/02/2022
Online Convolutional Re-parameterization
Structural re-parameterization has drawn increasing attention in various...
research
∙
03/18/2022
Beyond a Video Frame Interpolator: A Space Decoupled Learning Approach to Continuous Image Transition
Video frame interpolation (VFI) aims to improve the temporal resolution ...
research
∙
10/31/2021
PANet: Perspective-Aware Network with Dynamic Receptive Fields and Self-Distilling Supervision for Crowd Counting
Crowd counting aims to learn the crowd density distributions and estimat...
research
∙
04/29/2021
Discriminative-Generative Dual Memory Video Anomaly Detection
Recently, people tried to use a few anomalies for video anomaly detectio...
research
∙
02/04/2021
Active Boundary Loss for Semantic Segmentation
This paper proposes a novel active boundary loss for semantic segmentati...
research
∙
11/19/2020
DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation
Binary grid mask representation is broadly used in instance segmentation...
research
∙
09/26/2020
Causal Intervention for Weakly-Supervised Semantic Segmentation
We present a causal inference framework to improve Weakly-Supervised Sem...
research
∙
07/18/2020
Feature Pyramid Transformer
Feature interactions across space and scales underpin modern visual reco...
research
∙
05/26/2020
Towards Fine-grained Human Pose Transfer with Detail Replenishing Network
Human pose transfer (HPT) is an emerging research topic with huge potent...
research
∙
04/03/2020
Gradient Centralization: A New Optimization Technique for Deep Neural Networks
Optimization techniques are of great importance to effectively and effic...
research
∙
11/21/2019
Quantization Networks
Although deep neural networks are highly effective, their high computati...
research
∙
11/20/2019
SSAH: Semi-supervised Adversarial Deep Hashing with Self-paced Hard Sample Generation
Deep hashing methods have been proved to be effective and efficient for ...
research
∙
06/07/2019
Extracting Visual Knowledge from the Internet: Making Sense of Image Data
Recent successes in visual recognition can be primarily attributed to fe...
research
∙
04/19/2019
Automated Segmentation of Pulmonary Lobes using Coordination-Guided Deep Neural Networks
The identification of pulmonary lobes is of great importance in disease ...
research
∙
12/14/2018
Deep Active Learning for Video-based Person Re-identification
It is prohibitively expensive to annotate a large-scale video-based pers...
research
∙
12/05/2018
Dynamic Spatio-temporal Graph-based CNNs for Traffic Prediction
Accurate traffic forecast is a challenging problem due to the large-scal...
research
∙
04/24/2018
Homocentric Hypersphere Feature Embedding for Person Re-identification
Person re-identification (Person ReID) is a challenging task due to the ...
research
∙
03/16/2017
Refining Image Categorization by Exploiting Web Images and General Corpus
Studies show that refining real-world categories into semantic subcatego...
research
∙
11/22/2016