Related papers: Context Enhanced Transformer for Single Image Obje…
Recently, object detection models have witnessed notable performance improvements, particularly with transformer-based models. However, new objects frequently appear in the real world, requiring detection models to continually learn without…
Self-supervised pre-training and transformer-based networks have significantly improved the performance of object detection. However, most of the current self-supervised object detection methods are built on convolutional-based…
The DEtection TRansformer (DETR) opened new possibilities for object detection by modeling it as a translation task: converting image features into object-level representations. Previous works typically add expensive modules to DETR to…
Object detection with Transformers (DETR) has achieved a competitive performance over traditional detectors, such as Faster R-CNN. However, the potential of DETR remains largely unexplored for the more challenging task of arbitrary-oriented…
Object detection is one of the most active areas in computer vision, which has made significant improvement in recent years. Current state-of-the-art object detection methods mostly adhere to the framework of regions with convolutional…
Temporal modeling of objects is a key challenge in multiple object tracking (MOT). Existing methods track by associating detections through motion-based and appearance-based similarity heuristics. The post-processing nature of association…
We consider the problem of localizing a spatio-temporal tube in a video corresponding to a given text query. This is a challenging task that requires the joint and efficient modeling of temporal, spatial and multi-modal interactions. To…
Current Deep Learning methods for environment segmentation and velocity estimation rely on Convolutional Recurrent Neural Networks to exploit spatio-temporal relationships within obtained sensor data. These approaches derive scene dynamics…
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…
Current methods for Video Moment Retrieval (VMR) struggle to align complex situations involving specific environmental details, character descriptions, and action narratives. To tackle this issue, we propose a Large Language Model-guided…
We present Recurrent Vision Transformers (RVTs), a novel backbone for object detection with event cameras. Event cameras provide visual information with sub-millisecond latency at a high-dynamic range and with strong robustness against…
Semantic segmentation assigns labels to pixels in images, a critical yet challenging task in computer vision. Convolutional methods, although capturing local dependencies well, struggle with long-range relationships. Vision Transformers…
Video Referring Expression Comprehension (REC) aims to localize a target object in videos based on the queried natural language. Recent improvements in video REC have been made using Transformer-based methods with learnable queries.…
Object detection and tracking in videos represent essential and computationally demanding building blocks for current and future visual perception systems. In order to reduce the efficiency gap between available methods and computational…
Advanced deep Convolutional Neural Networks (CNNs) have shown great success in video-based person Re-Identification (Re-ID). However, they usually focus on the most obvious regions of persons with a limited global representation ability.…
Recently, Transformer-based methods, which predict polygon points or Bezier curve control points for localizing texts, are popular in scene text detection. However, these methods built upon detection transformer framework might achieve…
Image-to-video adaptation seeks to efficiently adapt image models for use in the video domain. Instead of finetuning the entire image backbone, many image-to-video adaptation paradigms use lightweight adapters for temporal modeling on top…
Temporal Grounding is to identify specific moments or highlights from a video corresponding to textual descriptions. Typical approaches in temporal grounding treat all video clips equally during the encoding process regardless of their…
Video salient object detection aims to find the most visually distinctive objects in a video. To explore the temporal dependencies, existing methods usually resort to recurrent neural networks or optical flow. However, these approaches…
Existing Visual Object Tracking (VOT) only takes the target area in the first frame as a template. This causes tracking to inevitably fail in fast-changing and crowded scenes, as it cannot account for changes in object appearance between…