Related papers: Deformable DETR: Deformable Transformers for End-t…

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…

Human Mesh Recovery (HMR) is an important yet challenging problem with applications across various domains including motion capture, augmented reality, and biomechanics. Accurately predicting human pose parameters from a single image…

Modern detection transformers (DETRs) use a set of object queries to predict a list of bounding boxes, sort them by their classification confidence scores, and select the top-ranked predictions as the final detection results for the given…

Video Moment Retrieval and Highlight Detection aim to find corresponding content in the video based on a text query. Existing models usually first use contrastive learning methods to align video and text features, then fuse and extract…

Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant…

Human-Object Interaction (HOI) detection is the task of identifying a set of <human, object, interaction> triplets from an image. Recent work proposed transformer encoder-decoder architectures that successfully eliminated the need for many…

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…

Detection transformer (DETR) relies on one-to-one assignment, assigning one ground-truth object to one prediction, for end-to-end detection without NMS post-processing. It is known that one-to-many assignment, assigning one ground-truth…

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,…

In this report, we present RT-DETRv2, an improved Real-Time DEtection TRansformer (RT-DETR). RT-DETRv2 builds upon the previous state-of-the-art real-time detector, RT-DETR, and opens up a set of bag-of-freebies for flexibility and…

Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit…

The use of intelligent automation is growing significantly in the automotive industry, as it assists drivers and fleet management companies, thus increasing their productivity. Dash cams are now been used for this purpose which enables the…

Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transformations. In this paper, we design a framework for training…

Surface defect detection is an extremely crucial step to ensure the quality of industrial products. Nowadays, convolutional neural networks (CNNs) based on encoder-decoder architecture have achieved tremendous success in various defect…

Temporal Action Detection (TAD) is challenging but fundamental for real-world video applications. Recently, DETR-based models have been devised for TAD but have not performed well yet. In this paper, we point out the problem in the…

This paper is concerned with the matching stability problem across different decoder layers in DEtection TRansformers (DETR). We point out that the unstable matching in DETR is caused by a multi-optimization path problem, which is…

Recently, deep-learning-based approaches have been widely studied for deformable image registration task. However, most efforts directly map the composite image representation to spatial transformation through the convolutional neural…

Multi-object tracking (MOT) in videos remains challenging due to complex object motions and crowded scenes. Recent DETR-based frameworks offer end-to-end solutions but typically process detection and tracking queries jointly within a single…

Small target detection in UAV imagery faces significant challenges such as scale variations, dense distribution, and the dominance of small targets. Existing algorithms rely on manually designed components, and general-purpose detectors are…

An important challenge in vision-based action recognition is the embedding of spatiotemporal features with two or more heterogeneous modalities into a single feature. In this study, we propose a new 3D deformable transformer for action…