Skip to search formSkip to main contentSkip to account menu
  • Publications
  • Influence
Saliency-aware geodesic video object segmentation
TLDR
This work introduces an unsupervised, geodesic distance based, salient video object segmentation method that incorporates saliency as prior for object via the computation of robust geodesIC measurement and builds global appearance models for foreground and background.
View on IEEE
Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection
TLDR
This paper proposes a fast video salient object detection model, based on a novel recurrent network architecture, named Pyramid Dilated Bidirectional ConvLSTM (PDB-ConvL STM), which achieves state-of-the-art results on two popular benchmarks, well demonstrating its superior performance and high applicability.
View via Publisher
Consistent Video Saliency Using Local Gradient Flow Optimization and Global Refinement
TLDR
The proposed spatiotemporal saliency detection method is robust enough to estimate the object and background in complex scenes with various motion patterns and appearances and introduces local as well as global contrast saliency measures using the foreground and background information estimated from the gradient flow field.
View on IEEE
Video Salient Object Detection via Fully Convolutional Networks
TLDR
A novel data augmentation technique that simulates video training data from existing annotated image data sets, which enables the deep video saliency network to learn diverse saliency information and prevents overfitting with the limited number of training videos.
View on IEEE
PraNet: Parallel Reverse Attention Network for Polyp Segmentation
TLDR
Quantitative and qualitative evaluations on five challenging datasets across six metrics show that the PraNet improves the segmentation accuracy significantly, and presents a number of advantages in terms of generalizability, and real-time segmentation efficiency.
View PDF on arXiv
Revisiting Video Saliency: A Large-Scale Benchmark and a New Model
TLDR
This work introduces a new benchmark for predicting human eye movements during dynamic scene free-viewing, and proposes a novel video saliency model that augments the CNN-LSTM network architecture with an attention mechanism to enable fast, end-to-end saliency learning.
View on IEEE
Camouflaged Object Detection
TLDR
A simple but effective framework for COD, termed Search Identification Network (SINet), which outperforms various state-of-the-art object detection baselines on all datasets tested, making it a robust, general framework that can help facilitate future research in COD.
View on IEEE
Learning Human-Object Interactions by Graph Parsing Neural Networks
This paper addresses the task of detecting and recognizing human-object interactions (HOI) in images and videos. We introduce the Graph Parsing Neural Network (GPNN), a framework that incorporates…
View PDF on arXiv
Deep Learning for Person Re-Identification: A Survey and Outlook
TLDR
A powerful AGW baseline is designed, achieving state-of-the-art or at least comparable performance on twelve datasets for four different Re-ID tasks, and a new evaluation metric (mINP) is introduced, indicating the cost for finding all the correct matches, which provides an additional criteria to evaluate the Re- ID system for real applications.
View on IEEE
Deep Visual Attention Prediction
TLDR
This model is based on a skip-layer network structure, which predicts human attention from multiple convolutional layers with various reception fields, and incorporates multi-level saliency predictions within a single network, which significantly decreases the redundancy of previous approaches of learning multiple network streams with different input scales.
View on IEEE
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License