-
Chapter and Conference Paper
3D Mitochondria Instance Segmentation with Spatio-Temporal Transformers
Accurate 3D mitochondria instance segmentation in electron microscopy (EM) is a challenging problem and serves as a prerequisite to empirically analyze their distributions and morphology. Most existing approac...
-
Chapter and Conference Paper
A Spatial-Temporal Deformable Attention Based Framework for Breast Lesion Detection in Videos
Detecting breast lesion in videos is crucial for computer-aided diagnosis. Existing video-based breast lesion detection approaches typically perform temporal feature aggregation of deep backbone features based...
-
Chapter and Conference Paper
Cross-Modulated Few-Shot Image Generation for Colorectal Tissue Classification
In this work, we propose a few-shot colorectal tissue image generation method for addressing the scarcity of histopathological training data for rare cancer tissues. Our few-shot generation method, named XM-GA...
-
Chapter and Conference Paper
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications
In the pursuit of achieving ever-increasing accuracy, large and complex neural networks are usually developed. Such models demand high computational resources and therefore cannot be deployed on edge devices. ...
-
Chapter and Conference Paper
PS-ARM: An End-to-End Attention-Aware Relation Mixer Network for Person Search
Person search is a challenging problem with various real-world applications, that aims at joint person detection and re-identification of a query person from uncropped gallery images. Although, previous study ...
-
Chapter and Conference Paper
DoodleFormer: Creative Sketch Drawing with Transformers
Creative sketching or doodling is an expressive activity, where imaginative and previously unseen depictions of everyday visual objects are drawn. Creative sketch image generation is a challenging vision probl...
-
Chapter and Conference Paper
Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer
State-of-the-art transformer-based video instance segmentation (VIS) approaches typically utilize either single-scale spatio-temporal features or per-frame multi-scale features during the attention computation...
-
Chapter and Conference Paper
Class-Agnostic Object Detection with Multi-modal Transformer
What constitutes an object? This has been a long-standing question in computer vision. Towards this goal, numerous learning-free and learning-based approaches have been developed to score objectness. However, the...
-
Article
Open AccessCompact Deep Color Features for Remote Sensing Scene Classification
Aerial scene classification is a challenging problem in understanding high-resolution remote sensing images. Most recent aerial scene classification approaches are based on Convolutional Neural Networks (CNNs)...
-
Chapter and Conference Paper
Count- and Similarity-Aware R-CNN for Pedestrian Detection
Recent pedestrian detection methods generally rely on additional supervision, such as visible bounding-box annotations, to handle heavy occlusions. We propose an approach that leverages pedestrian count and pr...
-
Chapter and Conference Paper
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
Single-stage instance segmentation approaches have recently gained popularity due to their speed and simplicity, but are still lagging behind in accuracy, compared to two-stage methods. We propose a fast singl...
-
Chapter and Conference Paper
Multi-stream Convolutional Networks for Indoor Scene Recognition
Convolutional neural networks (CNNs) have recently achieved outstanding results for various vision tasks, including indoor scene understanding. The de facto practice employed by state-of-the-art indoor scene r...
-
Article
Open AccessScale coding bag of deep features for human attribute and action recognition
Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding. ...
-
Chapter and Conference Paper
Top-Down Deep Appearance Attention for Action Recognition
Recognizing human actions in videos is a challenging problem in computer vision. Recently, convolutional neural network based deep features have shown promising results for action recognition. In this paper, w...
-
Chapter and Conference Paper
Deep Semantic Pyramids for Human Attributes and Action Recognition
Describing persons and their actions is a challenging problem due to variations in pose, scale and viewpoint in real-world images. Recently, semantic pyramids approach [1] for pose normalization has shown to prov...
-
Article
Coloring Action Recognition in Still Images
In this article we investigate the problem of human action recognition in static images. By action recognition we intend a class of problems which includes both action classification and action detection (i.e....
-
Chapter and Conference Paper
Opponent Colors for Human Detection
Human detection is a key component in fields such as advanced driving assistance and video surveillance. However, even detecting non-occluded standing humans remains a challenge of intensive research. Finding ...