Related papers: REJEPA: A Novel Joint-Embedding Predictive Archite…

Joint Embedding Predictive Architectures (JEPA) are a novel self supervised training technique that have shown recent promise across domains. We introduce BERT-JEPA (BEPA), a training paradigm that adds a JEPA training objective to…

Learning efficient representations for decision-making policies is a challenge in imitation learning (IL). Current IL methods require expert demonstrations, which are expensive to collect. Additionally, they are not explicitly trained to…

In wireless networked control systems, ensuring timely and reliable state updates from distributed devices to remote controllers is essential for robust control performance. However, when multiple devices transmit high-dimensional states…

Recently, there has been increasing interest in multimodal applications that integrate text with other modalities, such as images, audio and video, to facilitate natural language interactions with multimodal AI systems. While applications…

Sketch-based image retrieval (SBIR) has undergone an increasing interest in the community of computer vision bringing high impact in real applications. For instance, SBIR brings an increased benefit to eCommerce search engines because it…

Deep learning-based methods have garnered significant attention in remote sensing (RS) image compression due to their superior performance. Most of these methods focus on enhancing the coding capability of the compression network and…

This paper addresses the problem of self-supervised general-purpose audio representation learning. We explore the use of Joint-Embedding Predictive Architectures (JEPA) for this task, which consists of splitting an input mel-spectrogram…

Remote sensing image-text retrieval plays a crucial role in remote sensing interpretation, yet remains challenging under both closed-domain and open-domain scenarios due to semantic noise and domain shifts. To address these issues, we…

Ultrasound (US) imaging poses unique challenges for representation learning due to its inherently noisy acquisition process. The low signal-to-noise ratio and stochastic speckle patterns hinder standard self-supervised learning methods…

High-resolution remote sensing analysis faces challenges in global context modeling due to scene complexity and scale diversity. While CNNs excel at local feature extraction via parameter sharing, their fixed receptive fields fundamentally…

Vision-Language Pre-training (VLP) models like CLIP have significantly advanced Remote Sensing Image-Text Retrieval (RSITR). However, existing methods predominantly rely on coarse-grained global alignment, which often overlooks the dense,…

Content-based image retrieval (CBIR) of medical images is a crucial task that can contribute to a more reliable diagnosis if applied to big data. Recent advances in feature extraction and classification have enormously improved CBIR results…

Channel state information (CSI) provides a widely available sensing modality for human and environment perception, but existing CSI sensing models usually rely on task-specific supervised training and require substantial labeled data for…

Rapid advances in GPU hardware and multiple areas of Deep Learning open up a new opportunity for billion-scale information retrieval with exhaustive search. Building on top of the powerful concept of semantic learning, this paper proposes a…

Representation learning stands as one of the critical machine learning techniques across various domains. Through the acquisition of high-quality features, pre-trained embeddings significantly reduce input space redundancy, benefiting…

Image captioning aims to generate natural language descriptions for input images in an open-form manner. To accurately generate descriptions related to the image, a critical step in image captioning is to identify objects and understand…

In the Bag-of-Words (BoW) model based image retrieval task, the precision of visual matching plays a critical role in improving retrieval performance. Conventionally, local cues of a keypoint are employed. However, such strategy does not…

Embedding models have become essential for retrieval-augmented generation (RAG) tasks, semantic clustering, and text re-ranking. But despite their growing use, many of these come with notable limitations. For example, Jina fails to capture…

We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning robust speech representations. Stage~1 uses JEPA with DAAM…

Image captioning and cross-modal retrieval are examples of tasks that involve the joint analysis of visual and linguistic information. In connection to remote sensing imagery, these tasks can help non-expert users in extracting relevant…