Search Results for author:
Found 6 papers, 1 papers with code
Design and Analysis of Efficient Attention in Transformers for Social Group Activity Recognition
Social group activity recognition is a challenging task extended from group activity recognition, where social groups must be recognized with their activities and group members.
Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detection
Using the generated embeddings as training data, a feed-forward neural network learns to extract features of normal and anomaly from CLIP's embeddings, and as a result, a category-agnostic anomaly detector can be obtained without any training images.
Hunting Group Clues with Transformers for Social Group Activity Recognition
Our method is designed in such a way that the attention modules identify and then aggregate features relevant to social group activities, generating an effective feature for each social group.
Ranked #1 on
Group Activity Recognition
on Collective Activity
(using extra training data)
Segmentation-Based Bounding Box Generation for Omnidirectional Pedestrian Detection
We propose a segmentation-based bounding box generation method for omnidirectional pedestrian detection that enables detectors to tightly fit bounding boxes to pedestrians without omnidirectional images for training.
QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information
We propose a simple, intuitive yet powerful method for human-object interaction (HOI) detection.
Human-Object Interaction Concept Discovery
Human-Object Interaction Detection
Augmented Hard Example Mining for Generalizable Person Re-Identification
Although the performance of person re-identification (Re-ID) has been much improved by using sophisticated training methods and large-scale labelled datasets, many existing methods make the impractical assumption that information of a target domain can be utilized during training.
General Classification
Generalizable Person Re-identification
