Related papers: Beyond Hungarian: Match-Free Supervision for End-t…

This paper presents a novel training method for end-to-end scene text recognition. End-to-end scene text recognition offers high recognition accuracy, especially when using the encoder-decoder model based on Transformer. To train a highly…

During training, supervised object detection tries to correctly match the predicted bounding boxes and associated classification scores to the ground truth. This is essential to determine which predictions are to be pushed towards which…

In the recent years, we have witnessed a paradigm shift in the field of Computer Vision, with the forthcoming of the transformer architecture. Detection Transformers has become a state of the art solution to object detection and is a…

In this paper, we propose a novel integrated framework for learning both text detection and recognition. For most of the existing methods, detection and recognition are treated as two isolated tasks and trained separately, since parameters…

Tracking by detection, the dominant approach for online multi-object tracking, alternates between localization and association steps. As a result, it strongly depends on the quality of instantaneous observations, often failing when objects…

In this paper, we provide the observation that too few queries assigned as positive samples in DETR with one-to-one set matching leads to sparse supervision on the encoder's output which considerably hurt the discriminative feature learning…

Drone detection is pivotal in numerous security and counter-UAV applications. However, existing deep learning-based methods typically struggle to balance robust feature representation with computational efficiency. This challenge is…

Recently, object detection models have witnessed notable performance improvements, particularly with transformer-based models. However, new objects frequently appear in the real world, requiring detection models to continually learn without…

This paper takes an important step in bridging the performance gap between DETR and R-CNN for graphical object detection. Existing graphical object detection approaches have enjoyed recent enhancements in CNN-based object detection methods,…

Knowledge-Intensive Visual Question Answering (KI-VQA) refers to answering a question about an image whose answer does not lie in the image. This paper presents a new pipeline for KI-VQA tasks, consisting of a retriever and a reader. First,…

We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a…

With the increasing importance of video data in real-world applications, there is a rising need for efficient object detection methods that utilize temporal information. While existing video object detection (VOD) techniques employ various…

Human-Object Interaction detection is a holistic visual recognition task that entails object detection as well as interaction classification. Previous works of HOI detection has been addressed by the various compositions of subset…

Text detection and recognition in natural images have long been considered as two separate tasks that are processed sequentially. Training of two tasks in a unified framework is non-trivial due to significant dif- ferences in optimisation…

Convolutional Neural Networks (CNN) have dominated the field of detection ever since the success of AlexNet in ImageNet classification [12]. With the sweeping reform of Transformers [27] in natural language processing, Carion et al. [2]…

The majority of contemporary object-tracking approaches do not model interactions between objects. This contrasts with the fact that objects' paths are not independent: a cyclist might abruptly deviate from a previously planned trajectory…

Currently, domestic service robots have an insufficient ability to interact naturally through language. This is because understanding human instructions is complicated by various ambiguities and missing information. In existing methods, the…

Most modern multiple object tracking (MOT) systems follow the tracking-by-detection paradigm, consisting of a detector followed by a method for associating detections into tracks. There is a long history in tracking of combining motion and…

Object detection in Unmanned Aerial Vehicle (UAV) imagery is fundamentally challenged by a prevalence of small, densely packed, and occluded objects within cluttered backgrounds. Conventional detectors struggle with this domain, as they…

We consider the problem of omni-supervised object detection, which can use unlabeled, fully labeled and weakly labeled annotations, such as image tags, counts, points, etc., for object detection. This is enabled by a unified architecture,…