相关论文: Query matching for spatio-temporal action detectio…

One-to-one set matching is a key design for DETR to establish its end-to-end capability, so that object detection does not require a hand-crafted NMS (non-maximum suppression) to remove duplicate detections. This end-to-end signature is…

This paper presents LP-DETR (Layer-wise Progressive DETR), a novel approach that enhances DETR-based object detection through multi-scale relation modeling. Our method introduces learnable spatial relationships between object queries…

Object detection is one of the most significant aspects of computer vision, and it has achieved substantial results in a variety of domains. It is worth noting that there are few studies focusing on slender object detection. CNNs are widely…

The DETR object detection approach applies the transformer encoder and decoder architecture to detect objects and achieves promising performance. In this paper, we present a simple approach to address the main problem of DETR, the slow…

Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on…

Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this complementary information to improve detection. Therefore,…

We introduce DEIM, an innovative and efficient training framework designed to accelerate convergence in real-time object detection with Transformer-based architectures (DETR). To mitigate the sparse supervision inherent in one-to-one (O2O)…

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,…

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…

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…

Dense object detection is widely used in automatic driving, video surveillance, and other fields. This paper focuses on the challenging task of dense object detection. Currently, detection methods based on greedy algorithms, such as…

Based on analyzing the character of cascaded decoder architecture commonly adopted in existing DETR-like models, this paper proposes a new decoder architecture. The cascaded decoder architecture constrains object queries to update in the…

The introduction of DETR represents a new paradigm for object detection. However, its decoder conducts classification and box localization using shared queries and cross-attention layers, leading to suboptimal results. We observe that…

We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to model long-term temporal appearance and motion dynamics. The…

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…

Visual-based 3D semantic occupancy perception is a key technology for robotics, including autonomous vehicles, offering an enhanced understanding of the environment by 3D. This approach, however, typically requires more computational…

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…

Keypoint detection and tracking in traditional image frames are often compromised by image quality issues such as motion blur and extreme lighting conditions. Event cameras offer potential solutions to these challenges by virtue of their…

Incremental object detection (IOD) aims to sequentially learn new classes, while maintaining the capability to locate and identify old ones. As the training data arrives with annotations only with new classes, IOD suffers from catastrophic…

Spatio-temporal action detection in videos requires localizing the action both spatially and temporally in the form of an "action tube". Nowadays, most spatio-temporal action detection datasets (e.g. UCF101-24, AVA, DALY) are annotated with…