相关论文: Box-DETR: Understanding and Boxing Conditional Spa…

The objective of augmented reality (AR) is to add digital content to natural images and videos to create an interactive experience between the user and the environment. Scene analysis and object recognition play a crucial role in AR, as…

DETR-like models have significantly boosted the performance of detectors and even outperformed classical convolutional models. However, all tokens are treated equally without discrimination brings a redundant computational burden in the…

We propose ST-DETR, a Spatio-Temporal Transformer-based architecture for object detection from a sequence of temporal frames. We treat the temporal frames as sequences in both space and time and employ the full attention mechanisms to take…

Click-through rate (CTR) prediction is fundamental to online advertising systems. While Deep Learning Recommendation Models (DLRMs) with explicit feature interactions have long dominated this domain, recent advances in generative…

We introduce a highly performant 3D object detector for point clouds using the DETR framework. The prior attempts all end up with suboptimal results because they fail to learn accurate inductive biases from the limited scale of training…

Tiny object detection plays a vital role in drone surveillance, remote sensing, and autonomous systems, enabling the identification of small targets across vast landscapes. However, existing methods suffer from inefficient feature leverage…

Existing oriented object detection methods commonly use metric AP$_{50}$ to measure the performance of the model. We argue that AP$_{50}$ is inherently unsuitable for oriented object detection due to its large tolerance in angle deviation.…

Transformers have recently gained attention in the computer vision domain due to their ability to model long-range dependencies. However, the self-attention mechanism, which is the core part of the Transformer model, usually suffers from…

The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection frameworks, such as Faster-RCNN. However, DETR suffers from…

Query-based object detectors directly decode image features into object instances with a set of learnable queries. These query vectors are progressively refined to stable meaningful representations through a sequence of decoder layers, and…

Moving Object Detection (MOD) is a crucial task for the Autonomous Driving pipeline. MOD is usually handled via 2-stream convolutional architectures that incorporates both appearance and motion cues, without considering the inter-relations…

Center-aligned regression remains dominant in LiDAR-based 3D object detection, yet it suffers from fundamental instability: object centers often fall in sparse or empty regions of the bird's-eye-view (BEV) due to the front-surface-biased…

Temporal action proposal generation is an important and challenging task in video understanding, which aims at detecting all temporal segments containing action instances of interest. The existing proposal generation approaches are…

We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. We show that the slow convergence results…

Table detection within document images is a crucial task in document processing, involving the identification and localization of tables. Recent strides in deep learning have substantially improved the accuracy of this task, but it still…

Cross-domain object detection is more challenging than object classification since multiple objects exist in an image and the location of each object is unknown in the unlabeled target domain. As a result, when we adapt features of…

In this paper, we propose EDIT (Encoder-Decoder Image Transformer), a novel architecture designed to mitigate the attention sink phenomenon observed in Vision Transformer models. Attention sink occurs when an excessive amount of attention…

This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage. We review the training process and attribute the overlooked phenomenon to two…

When recalling information in conversation, people often arrive at the recollection after multiple turns. However, existing benchmarks for evaluating agent capabilities in such tip-of-the-tongue search processes are restricted to…

In most modern object detection pipelines, the detection proposals are processed independently given the feature map. Therefore, they overlook the underlying relationships between objects and the surrounding background, which could have…