This paper presents a new approach for segmenting and tracking moving objects in complex visual scenes. The method is based on refining optical flow predictions using appearance-based information. It employs…
Continue readingThe paper presents a two-step method for dynamic obstacle avoidance (DOA) in autonomous vehicles, crucial for any vehicle operating in sea, air, or land. The proposed architecture combines supervised and…
Continue readingThe article discusses a learning framework that allows robots to simulate their own kinematics and motor control just by observing their movements in a mirror-like manner. This self-learned simulation enables…
Continue readingThe article introduces Fast Language-Audio Pre-training (FLAP), a self-supervised learning approach that learns to align audio and language representations through masking, contrastive learning, and reconstruction. FLAP randomly drops audio spectrogram…
Continue readingThe article presents an in-depth study of foundation models tailored for music informatics, a domain challenged by the scarcity of labeled data and generalization issues. The researchers conducted a comparative…
Continue readingThe paper presents a novel method called Geometric Harmonization (GH) to address the issue of representation learning disparity in self-supervised learning (SSL), particularly under long-tailed distribution scenarios. Traditional SSL methods…
Continue readingThe article discusses the challenges in speech generation using discrete audio tokens derived from self-supervised learning models. It suggests that the current practice of directly utilizing audio tokens complicates sequence…
Continue readingThe paper presents Fetal Ultrasound Semantic Clustering (FUSC), an unsupervised method that automates the clustering of ultrasound images into various fetal views. This approach eliminates the need for labor-intensive manual…
Continue readingThe 2023 Multilingual Speech Universal Performance Benchmark (ML-SUPERB) Challenge expands on the acclaimed SUPERB framework. It emphasizes self-supervised models in multilingual speech recognition and language identification. The challenge consists of…
Continue readingThe article presents a new method called Point Regress AutoEncoder (Point-RAE) for regressive autoencoders in point cloud self-supervised learning. The method decouples functions between the decoder and encoder by introducing…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
