相关论文: Spatial-Temporal Graph Enhanced DETR Towards Multi…

The recently proposed end-to-end transformer detectors, such as DETR and Deformable DETR, have a cascade structure of stacking 6 decoder layers to update object queries iteratively, without which their performance degrades seriously. In…

Recent DEtection TRansformer-based (DETR) models have obtained remarkable performance. Its success cannot be achieved without the re-introduction of multi-scale feature fusion in the encoder. However, the excessively increased tokens in…

Session-based recommendation plays a central role in a wide spectrum of online applications, ranging from e-commerce to online advertising services. However, the majority of existing session-based recommendation techniques (e.g.,…

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…

Detection Transformers (DETR) are renowned object detection pipelines, however computationally efficient multiscale detection using DETR is still challenging. In this paper, we propose a Cross-Resolution Encoding-Decoding (CRED) mechanism…

Generic event boundary detection is an important yet challenging task in video understanding, which aims at detecting the moments where humans naturally perceive event boundaries. The main challenge of this task is perceiving various…

DEtection TRansformer (DETR) started a trend that uses a group of learnable queries for unified visual perception. This work begins by applying this appealing paradigm to LiDAR-based point cloud segmentation and obtains a simple yet…

For a given video-based Human-Object Interaction scene, modeling the spatio-temporal relationship between humans and objects are the important cue to understand the contextual information presented in the video. With the effective…

Vision Transformers (ViTs) have achieved remarkable success in computer vision tasks. However, their potential in rotation-sensitive scenarios has not been fully explored, and this limitation may be inherently attributed to the lack of…

Previous studies on event camera sensing have demonstrated certain detection performance using dense event representations. However, the accumulated noise in such dense representations has received insufficient attention, which degrades the…

The recent detection transformer (DETR) simplifies the object detection pipeline by removing hand-crafted designs and hyperparameters as employed in conventional two-stage object detectors. However, how to leverage the simple yet effective…

3D object detection plays an important role in autonomous driving and other robotics applications. However, these detectors usually require training on large amounts of annotated data that is expensive and time-consuming to collect.…

We propose 3DETR, an end-to-end Transformer based object detection model for 3D point clouds. Compared to existing detection methods that employ a number of 3D-specific inductive biases, 3DETR requires minimal modifications to the vanilla…

In this paper, we propose a simple and strong framework for Tracking Any Point with TRansformers (TAPTR). Based on the observation that point tracking bears a great resemblance to object detection and tracking, we borrow designs from…

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…

This paper presents a general scheme for enhancing the convergence and performance of DETR (DEtection TRansformer). We investigate the slow convergence problem in transformers from a new perspective, suggesting that it arises from the…

Events defined by the interaction of objects in a scene are often of critical importance; yet important events may have insufficient labeled examples to train a conventional deep model to generalize to future object appearance. Activity…

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…

DETR is the first end-to-end object detector using a transformer encoder-decoder architecture and demonstrates competitive performance but low computational efficiency on high resolution feature maps. The subsequent work, Deformable DETR,…

End-to-end Object Detection with Transformer (DETR)proposes to perform object detection with Transformer and achieve comparable performance with two-stage object detection like Faster-RCNN. However, DETR needs huge computational resources…