Related papers: DETRs with Hybrid Matching
Clothing segmentation and fine-grained attribute recognition are challenging tasks at the crossing of computer vision and fashion, which segment the entire ensemble clothing instances as well as recognize detailed attributes of the clothing…
The ability to detect and track the dynamic objects in different scenes is fundamental to real-world applications, e.g., autonomous driving and robot navigation. However, traditional Multi-Object Tracking (MOT) is limited to tracking…
Depth enhancement, which uses RGB images as guidance to convert raw signals from dToF into high-precision, dense depth maps, is a critical task in computer vision. Although existing super-resolution-based methods show promising results on…
Visual prompted object detection enables interactive and flexible definition of target categories, thereby facilitating open-vocabulary detection. Since visual prompts are derived directly from image features, they often outperform text…
This work proposes an attention-based sequence-to-sequence model for handwritten word recognition and explores transfer learning for data-efficient training of HTR systems. To overcome training data scarcity, this work leverages models…
End-to-end object detection is rapidly progressed after the emergence of DETR. DETRs use a set of sparse queries that replace the dense candidate boxes in most traditional detectors. In comparison, the sparse queries cannot guarantee a high…
Popular transformer detectors have achieved promising performance through query-based learning using attention mechanisms. However, the roles of existing decoder query types (e.g., content query and positional query) are still…
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…
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…
Recently, one-stage trackers that use a joint model to predict both detections and appearance embeddings in one forward pass received much attention and achieved state-of-the-art results on the Multi-Object Tracking (MOT) benchmarks.…
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]…
Few-shot object detection (FSOD), an efficient method for addressing the severe data-hungry problem, has been extensively discussed. Current works have significantly advanced the problem in terms of model and data. However, the overall…
Fully convolutional detectors discard the one-to-many assignment and adopt a one-to-one assigning strategy to achieve end-to-end detection but suffer from the slow convergence issue. In this paper, we revisit these two assignment methods…
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,…
Real-time object detection is crucial for real-world applications as it requires high accuracy with low latency. While Detection Transformers (DETR) have demonstrated significant performance improvements, current real-time DETR models are…
Transformers have revolutionized the object detection landscape by introducing DETRs, acclaimed for their simplicity and efficacy. Despite their advantages, the substantial size of these models poses significant challenges for practical…
Detection Transformer-based methods have achieved significant advancements in general object detection. However, challenges remain in effectively detecting small objects. One key difficulty is that existing encoders struggle to efficiently…
Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. However, the domain gap between synthetic and real images poses a challenge in acquiring feature representations…
Recent self-supervised methods are mainly designed for representation learning with the base model, e.g., ResNets or ViTs. They cannot be easily transferred to DETR, with task-specific Transformer modules. In this work, we present Siamese…
Modeling sparse and dense image matching within a unified functional correspondence model has recently attracted increasing research interest. However, existing efforts mainly focus on improving matching accuracy while ignoring its…