Related papers: MAL: Motion-Aware Loss with Temporal and Distillat…
Attributes of sound inherent to objects can provide valuable cues to learn rich representations for object detection and tracking. Furthermore, the co-occurrence of audiovisual events in videos can be exploited to localize objects over the…
Monocular Metric Depth Estimation (MMDE) is essential for physically intelligent systems, yet accurate depth estimation for underrepresented classes in complex scenes remains a persistent challenge. To address this, we propose RAD, a…
Although both self-supervised single-frame and multi-frame depth estimation methods only require unlabeled monocular videos for training, the information they leverage varies because single-frame methods mainly rely on appearance-based…
Unsupervised learning of depth and ego-motion from unlabelled monocular videos has recently drawn great attention, which avoids the use of expensive ground truth in the supervised one. It achieves this by using the photometric errors…
We address the challenging problem of learning motion representations using deep models for video recognition. To this end, we make use of attention modules that learn to highlight regions in the video and aggregate features for…
Unsupervised anomaly detection encompasses diverse applications in industrial settings where a high-throughput and precision is imperative. Early works were centered around one-class-one-model paradigm, which poses significant challenges in…
Multi-frame depth estimation improves over single-frame approaches by also leveraging geometric relationships between images via feature matching, in addition to learning appearance-based features. In this paper we revisit feature matching…
Understanding videos that contain multiple modalities is crucial, especially in egocentric videos, where combining various sensory inputs significantly improves tasks like action recognition and moment localization. However, real-world…
Depth completion is an important vision task, and many efforts have been made to enhance the quality of depth maps from sparse depth measurements. Despite significant advances, training these models to recover dense depth from sparse…
In self-supervised monocular depth estimation, the depth discontinuity and motion objects' artifacts are still challenging problems. Existing self-supervised methods usually utilize a single view to train the depth estimation network.…
Unsupervised monocular depth estimation techniques have demonstrated encouraging results but typically assume that the scene is static. These techniques suffer when trained on dynamical scenes, where apparent object motion can equally be…
Recent advancements in camera-based 3D object detection have introduced cross-modal knowledge distillation to bridge the performance gap with LiDAR 3D detectors, leveraging the precise geometric information in LiDAR point clouds. However,…
This paper introduces Smooth-Distill, a novel self-distillation framework designed to simultaneously perform human activity recognition (HAR) and sensor placement detection using wearable sensor data. The proposed approach utilizes a…
Deep metric learning (DML) aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval. Prior literature predominantly focuses on pair-based and proxy-based methods to…
We propose a self-supervised spatio-temporal matching method, coined Motion-Aware Mask Propagation (MAMP), for video object segmentation. MAMP leverages the frame reconstruction task for training without the need for annotations. During…
Deep Reinforcement Learning (DRL) based navigation methods have demonstrated promising results for mobile robots, but suffer from limited action flexibility in confined spaces. Conventional DRL approaches predominantly learn forward-motion…
Monocular depth estimation (MDE) from thermal images is a crucial technology for robotic systems operating in challenging conditions such as fog, smoke, and low light. The limited availability of labeled thermal data constrains the…
As a popular meta-learning approach, the model-agnostic meta-learning (MAML) algorithm has been widely used due to its simplicity and effectiveness. However, the convergence of the general multi-step MAML still remains unexplored. In this…
Training multimodal models requires a large amount of labeled data. Active learning (AL) aim to reduce labeling costs. Most AL methods employ warm-start approaches, which rely on sufficient labeled data to train a well-calibrated model that…
Changes in facial expression, head movement, body movement and gesture movement are remarkable cues in sign language recognition, and most of the current continuous sign language recognition(CSLR) research methods mainly focus on static…