Related papers: Accelerating Physical Property Reasoning for Augme…

Augmented data storytelling enhances narrative delivery by integrating visualizations with physical environments and presenter actions. Existing systems predominantly rely on body gestures or speech to control visualizations, leaving…

Estimation of 3D gaze is highly relevant to multiple fields, including but not limited to interactive systems, specialized human-computer interfaces, and behavioral research. Although recently deep learning methods have boosted the accuracy…

Vision-language models such as CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions due to pre-training on short and concise captions. We present FAST-GOAL…

Vision-Language Models (VLMs) have been increasingly integrated into object navigation tasks for their rich prior knowledge and strong reasoning abilities. However, applying VLMs to navigation poses two key challenges: effectively…

Deep neural networks deliver state-of-the-art visual recognition, but they rely on large datasets, which are time-consuming to annotate. These datasets are typically annotated in two stages: (1) determining the presence of object classes at…

In this paper we present an approach and a benchmark for visual reasoning in robotics applications, in particular small object grasping and manipulation. The approach and benchmark are focused on inferring object properties from visual and…

This thesis is part of a CIFRE agreement between the company Othello and the LIASD laboratory. The objective is to develop an artificial intelligence system that can detect real-time dangers in a video stream. To achieve this, a novel…

Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware…

Current neural architecture search (NAS) algorithms still require expert knowledge and effort to design a search space for network construction. In this paper, we consider automating the search space design to minimize human interference,…

Vision-Language Models (VLMs) offer a promising approach to end-to-end autonomous driving due to their human-like reasoning capabilities. However, troublesome gaps remains between current VLMs and real-world autonomous driving applications.…

Visual Saliency refers to the innate human mechanism of focusing on and extracting important features from the observed environment. Recently, there has been a notable surge of interest in the field of automotive research regarding the…

Intelligent anomaly detection in dynamic visual environments requires reconciling real-time performance with semantic interpretability. Conventional approaches address only fragments of this challenge. Reconstruction-based models capture…

Chain of Thought (CoT) reasoning enhances logical performance by decomposing complex tasks, yet its multimodal extension faces a trade-off. The prevailing Thinking with Images paradigm achieves visual refocusing by explicitly cropping image…

Integration of Large Language Models (LLMs) into visual domain tasks, resulting in visual-LLMs (V-LLMs), has enabled exceptional performance in vision-language tasks, particularly for visual question answering (VQA). However, existing…

Automatically describing an image with a natural language has been an emerging challenge in both fields of computer vision and natural language processing. In this paper, we present Long Short-Term Memory with Attributes (LSTM-A) - a novel…

As AI workloads drive increasing memory requirements, domain-specific accelerators need higher-density on-chip memory beyond what current SRAM scaling trends can provide. Simultaneously, the vast amounts of short-lived data in these…

Visual object tracking is a fundamental task in the field of computer vision. Recently, Siamese trackers have achieved state-of-the-art performance on recent benchmarks. However, Siamese trackers do not fully utilize semantic and objectness…

The present project aims to use machine learning, specifically neural networks (NN), to learn the trajectories of a set of coupled ordinary differential equations (ODEs) and decrease compute times for obtaining ODE solutions by using this…

In dynamic environments, performance of visual SLAM techniques can be impaired by visual features taken from moving objects. One solution is to identify those objects so that their visual features can be removed for localization and…

Multimodal large language models (MLLMs) are increasingly being applied to spatial cognition tasks, where they are expected to understand and interact with complex environments. Most existing works improve spatial reasoning by introducing…