Related papers: FOCUS: Fine-grained Optimization with Semantic Gui…
Pedestrian detection is a critical problem in computer vision with significant impact on safety in urban autonomous driving. In this work, we explore how semantic segmentation can be used to boost pedestrian detection accuracy while having…
Feature fusion modules from encoder and self-attention module have been adopted in semantic segmentation. However, the computation of these modules is costly and has operational limitations in real-time environments. In addition,…
Attention--or attribution--maps methods are methods designed to highlight regions of the model's input that were discriminative for its predictions. However, different attention maps methods can highlight different regions of the input,…
The challenges of high intra-class variance yet low inter-class fluctuations in fine-grained visual categorization are more severe with few labeled samples, \textit{i.e.,} Fine-Grained categorization problems under the Few-Shot setting…
Multi-object tracking (MOT) is a fundamental problem in computer vision with numerous applications, such as intelligent surveillance and automated driving. Despite the significant progress made in MOT, pedestrian attributes, such as gender,…
Micro-Expression Recognition has become challenging, as it is extremely difficult to extract the subtle facial changes of micro-expressions. Recently, several approaches proposed several expression-shared features algorithms for…
We propose a simple yet effective approach to the problem of pedestrian detection which outperforms the current state-of-the-art. Our new features are built on the basis of low-level visual features and spatial pooling. Incorporating…
Text contained in an image carries high-level semantics that can be exploited to achieve richer image understanding. In particular, the mere presence of text provides strong guiding content that should be employed to tackle a diversity of…
Fine-grained visual classification (FGVC) is challenging but more critical than traditional classification tasks. It requires distinguishing different subcategories with the inherently subtle intra-class object variations. Previous works…
Text-based person search aims to retrieve the matched pedestrians from a large-scale image database according to the text description. The core difficulty of this task is how to extract effective details from pedestrian images and texts,…
Deep metric learning is essential for visual recognition. The widely used pair-wise (or triplet) based loss objectives cannot make full use of semantical information in training samples or give enough attention to those hard samples during…
In this work, we propose a geometry-aware semi-supervised framework for fine-grained building function recognition, utilizing geometric relationships among multi-source data to enhance pseudo-label accuracy in semi-supervised learning,…
Generalizable semantic segmentation aims to perform well on unseen target domains, a critical challenge due to real-world applications requiring high generalizability. Class-wise prototypes, representing class centroids, serve as…
Semantic segmentation has recently achieved notable advances by exploiting "class-level" contextual information during learning. However, these approaches simply concatenate class-level information to pixel features to boost the pixel…
Video periocular recognition is the task of recognizing an individual's identity based on the region around an individual's eyes. The periocular area is one of the most discriminative regions of the human face, making it suitable for…
Unsupervised visible-infrared person re-identification (USL-VI-ReID) seeks to match pedestrian images of the same individual across different modalities without human annotations for model learning. Previous methods unify pseudo-labels of…
Adapting models pre-trained on large-scale datasets is a proven way to reach strong performance quickly for down-stream tasks. However, the growth of state-of-the-art mod-els makes traditional full fine-tuning unsuitable and difficult,…
This paper describes a fast and accurate semantic image segmentation approach that encodes not only the discriminative features from deep neural networks, but also the high-order context compatibility among adjacent objects as well as low…
To assist humans in efficiently validating RAG-generated content, developing a fine-grained attribution mechanism that provides supporting evidence from retrieved documents for every answer span is essential. Existing fine-grained…
Wearable computing and context awareness are the focuses of study in the field of artificial intelligence recently. One of the most appealing as well as challenging applications is the Human Activity Recognition (HAR) utilizing smart…