Zobrazeno 1 - 10
of 1 428
pro vyhledávání: '"Henriques, João"'
Autor:
Liang, Yichao, Kumar, Nishanth, Tang, Hao, Weller, Adrian, Tenenbaum, Joshua B., Silver, Tom, Henriques, João F., Ellis, Kevin
Broadly intelligent agents should form task-specific abstractions that selectively expose the essential elements of a task, while abstracting away the complexity of the raw sensorimotor space. In this work, we present Neuro-Symbolic Predicates, a fir
Externí odkaz:
http://arxiv.org/abs/2410.23156
Autor:
Longa, Marian, Henriques, João F.
Learning interpretable representations of visual data is an important challenge, to make machines' decisions understandable to humans and to improve generalisation outside of the training distribution. To this end, we propose a deep learning framewor
Externí odkaz:
http://arxiv.org/abs/2410.18539
Reconstructing realistic 3D human models from monocular images has significant applications in creative industries, human-computer interfaces, and healthcare. We base our work on 3D Gaussian Splatting (3DGS), a scene representation composed of a mixt
Externí odkaz:
http://arxiv.org/abs/2409.04196
Recent advancements in machine learning have fueled research on multimodal tasks, such as for instance text-to-video and text-to-audio retrieval. These tasks require models to understand the semantic content of video and audio data, including objects
Externí odkaz:
http://arxiv.org/abs/2409.00851
Autor:
Zhao, Chenxiao, Yang, Lin, Henriques, João C. G., Ferri-Cortés, Mar, Catarina, Gonçalo, Pignedoli, Carlo A., Ma, Ji, Feng, Xinliang, Ruffieux, Pascal, Fernández-Rossier, Joaquín, Fasel, Roman
Haldane's seminal work established two fundamentally different types of excitation spectra for antiferromagnetic Heisenberg quantum spin chains: gapped excitations in integer-spin chains and gapless excitations in half-integer-spin chains. In finite-
Externí odkaz:
http://arxiv.org/abs/2408.10045
Autor:
Bhalgat, Yash, Tschernezki, Vadim, Laina, Iro, Henriques, João F., Vedaldi, Andrea, Zisserman, Andrew
Egocentric videos present unique challenges for 3D scene understanding due to rapid camera motion, frequent object occlusions, and limited object visibility. This paper introduces a novel approach to instance segmentation and tracking in first-person
Externí odkaz:
http://arxiv.org/abs/2408.09860
Autor:
Fu, Xiaoshuai, Huang, Li, Liu, Kun, Henriques, João C. G., Gao, Yixuan, Han, Xianghe, Chen, Hui, Wang, Yan, Palma, Carlos-Andres, Cheng, Zhihai, Lin, Xiao, Du, Shixuan, Ma, Ji, Fernández-Rossier, Joaquín, Feng, Xinliang, Gao, Hong-Jun
Understanding and engineering the coupling of spins in nanomaterials is of central importance for designing novel devices. Graphene nanostructures with {\pi}-magnetism offer a chemically tunable platform to explore quantum magnetic interactions. Howe
Externí odkaz:
http://arxiv.org/abs/2407.20511
Autor:
Ishida, Shu, Henriques, João F.
This work compares ways of extending Reinforcement Learning algorithms to Partially Observed Markov Decision Processes (POMDPs) with options. One view of options is as temporally extended action, which can be realized as a memory that allows the agen
Externí odkaz:
http://arxiv.org/abs/2407.18913
Autor:
Longa, Marian, Henriques, João F.
Unsupervised object detection using deep neural networks is typically a difficult problem with few to no guarantees about the learned representation. In this work we present the first unsupervised object detection method that is theoretically guarant
Externí odkaz:
http://arxiv.org/abs/2406.07284
Autor:
Szymanowicz, Stanislaw, Insafutdinov, Eldar, Zheng, Chuanxia, Campbell, Dylan, Henriques, João F., Rupprecht, Christian, Vedaldi, Andrea
In this paper, we propose Flash3D, a method for scene reconstruction and novel view synthesis from a single image which is both very generalisable and efficient. For generalisability, we start from a "foundation" model for monocular depth estimation
Externí odkaz:
http://arxiv.org/abs/2406.04343