Related papers: ClickBAIT-v2: Training an Object Detector in Real-…

Attention guidance is an approach to addressing dataset bias in deep learning, where the model relies on incorrect features to make decisions. Focusing on image classification tasks, we propose an efficient human-in-the-loop system to…

Supervised training of object detectors requires well-annotated large-scale datasets, whose production is costly. Therefore, some efforts have been made to obtain annotations in economical ways, such as cloud sourcing. However, datasets…

Detecting change-points in data is challenging because of the range of possible types of change and types of behaviour of data when there is no change. Statistically efficient methods for detecting a change will depend on both of these…

We study active object tracking, where a tracker takes as input the visual observation (i.e., frame sequence) and produces the camera control signal (e.g., move forward, turn left, etc.). Conventional methods tackle the tracking and the…

Localizing an object accurately with respect to a robot is a key step for autonomous robotic manipulation. In this work, we propose to tackle this task knowing only 3D models of the robot and object in the particular case where the scene is…

Modern machine learning methods require significant amounts of labelled data, making the preparation process time-consuming and resource-intensive. In this paper, we propose to consider the process of prototyping a tool for annotating and…

We present an architecture and a training recipe that adapts pre-trained open-world image models to localization in videos. Understanding the open visual world (without being constrained by fixed label spaces) is crucial for many real-world…

Convolutional networks reach top quality in pixel-level video object segmentation but require a large amount of training data (1k~100k) to deliver such results. We propose a new training strategy which achieves state-of-the-art results…

Existing computer vision and object detection methods strongly rely on neural networks and deep learning. This active research area is used for applications such as autonomous driving, aerial photography, protection, and monitoring.…

We propose to leverage a generic object tracker in order to perform object mining in large-scale unlabeled videos, captured in a realistic automotive setting. We present a dataset of more than 360'000 automatically mined object tracks from…

Bounding-box annotation form has been the most frequently used method for visual object localization tasks. However, bounding-box annotation relies on a large amount of precisely annotating bounding boxes, and it is expensive and laborious.…

Recently, few-shot video classification has received an increasing interest. Current approaches mostly focus on effectively exploiting the temporal dimension in videos to improve learning under low data regimes. However, most works have…

Convolutional neural network (CNN) has drawn increasing interest in visual tracking owing to its powerfulness in feature extraction. Most existing CNN-based trackers treat tracking as a classification problem. However, these trackers are…

Object detection is one of the major problems in computer vision, and has been extensively studied. Most of the existing detection works rely on labor-intensive supervision, such as ground truth bounding boxes of objects or at least…

Recent works have shown that convolutional networks have substantially improved the performance of multiple object tracking by simultaneously learning detection and appearance features. However, due to the local perception of the…

Efficient and accurate object detection in video and image analysis is one of the major beneficiaries of the advancement in computer vision systems with the help of deep learning. With the aid of deep learning, more powerful tools evolved,…

Diffusion-based text-to-image generation models have demonstrated strong performance in terms of image quality and diversity. However, they still struggle to generate images that accurately reflect the number of objects specified in the…

Traditional video captioning requests a holistic description of the video, yet the detailed descriptions of the specific objects may not be available. Without associating the moving trajectories, these image-based data-driven methods cannot…

Deep SORT\cite{wojke2017simple} is a tracking-by-detetion approach to multiple object tracking with a detector and a RE-ID model. Both separately training and inference with the two model is time-comsuming. In this paper, we unify the…

Action recognition is an important problem that requires identifying actions in video by learning complex interactions across scene actors and objects. However, modern deep-learning based networks often require significant computation, and…