Concerns with enabling computers to interpret and understand visual inputs, such as images and videos.
The paper introduces a novel object-centric contact representation, ContactGen, for hand-object interaction. ContactGen comprises three components: a contact map indicating the contact location, a part map representing the contact hand…
Continue readingThe study focuses on improving large multimodal models (LMMs), specifically the LLaVA model, through visual instruction tuning. By using CLIP-ViT-L-336px with an MLP projection and adding academic-task-oriented VQA data, the…
Continue readingThe article presents Soft Convex Quantization (SCQ) as a solution to the challenges of Vector Quantization (VQ) in deep learning. VQ is a technique used for extracting discrete latent representations…
Continue readingThis article introduces a new method for audio-visual speech separation, called RTFS-Net. This method operates in the time-frequency domain and uses a multi-layered RNN to independently model and capture the…
Continue readingThe GENSIM project proposes an approach to generate rich simulation environments and expert demonstrations using large language models (LLM). It aims to address the challenge of task-level diversity in robotic…
Continue readingThe study introduces H-InDex, a learning framework that uses visual representations from human hands to enhance robotic hand dexterity. This method includes three stages: pre-training representations with 3D human hand…
Continue readingThe article discusses an emerging area called Representation Engineering (RepE). This approach aims to increase the transparency of AI systems using insights from cognitive neuroscience. RepE focuses on population-level representations…
Continue readingThe research explores the use of lightweight deep neural network architectures to enable Pepper, a humanoid robot, to understand and interpret American Sign Language (ASL). The goal is to facilitate…
Continue readingThe article introduces Prototype Generation, a robust form of feature visualisation for model-agnostic, data-independent interpretability of image classification models. It counters previous claims that feature visualisation algorithms are untrustworthy due…
Continue readingThis article discusses a new system for pedestrian data collection that is designed to aid in research on social navigation and pedestrian-robot interactions. The system uses machine learning methods and…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
