Search Results - "Cucurull, Guillem"

Deep Pain: Exploiting Long Short-Term Memory Networks for Facial Expression Classification by Rodriguez, Pau, Cucurull, Guillem, Gonzalez, Jordi, Gonfaus, Josep M., Nasrollahi, Kamal, Moeslund, Thomas B., Roca, F. Xavier

“…Pain is an unpleasant feeling that has been shown to be an important factor for the recovery of patients. Since this is costly in human resources and difficult…”
Get full text

BigBrain 3D atlas of cortical layers: Cortical and laminar thickness gradients diverge in sensory and motor cortices by Wagstyl, Konrad, Larocque, Stéphanie, Cucurull, Guillem, Lepage, Claude, Cohen, Joseph Paul, Bludau, Sebastian, Palomero-Gallagher, Nicola, Lewis, Lindsay B, Funck, Thomas, Spitzer, Hannah, Dickscheid, Timo, Fletcher, Paul C, Romero, Adriana, Zilles, Karl, Amunts, Katrin, Bengio, Yoshua, Evans, Alan C

“…Histological atlases of the cerebral cortex, such as those made famous by Brodmann and von Economo, are invaluable for understanding human brain microstructure…”
Get full text

Context-Aware Visual Compatibility Prediction by Cucurull, Guillem, Taslakian, Perouz, Vazquez, David

“…How do we determine whether two or more clothing items are compatible or visually appealing? Part of the answer lies in understanding of visual aesthetics, and…”
Get full text

Personality Trait Analysis in Social Networks Based on Weakly Supervised Learning of Shared Images by Rodríguez, Pau, Velazquez, Diego, Cucurull, Guillem, Gonfaus, Josep M., Roca, F. Xavier, Ozawa, Seiichi, Gonzàlez, Jordi

“…Social networks have attracted the attention of psychologists, as the behavior of users can be used to assess personality traits, and to detect sentiments and…”
Get full text

Age and gender recognition in the wild with deep attention by Rodríguez, Pau, Cucurull, Guillem, Gonfaus, Josep M., Roca, F. Xavier, Gonzàlez, Jordi

“…•A novel feedforward attention mechanism for CNNs is proposed.•The mechanism increases CNNs robustness to image deformations and clutter.•The proposed…”
Get full text

Pay Attention to the Activations: A Modular Attention Mechanism for Fine-Grained Image Recognition by Rodriguez, Pau, Velazquez, Diego, Cucurull, Guillem, Gonfaus, Josep M., Roca, F. Xavier, Gonzalez, Jordi

“…Fine-grained image recognition is central to many multimedia tasks such as search, retrieval, and captioning. Unfortunately, these tasks are still challenging…”
Get full text

Pay attention to the activations: a modular attention mechanism for fine-grained image recognition by López, Pau Rodríguez, Dorta, Diego Velazquez, Preixens, Guillem Cucurull, Gonfaus, Josep M, Marva, F. Xavier Roca, Sabaté, Jordi Gonzàlez

“…Fine-grained image recognition is central to many multimedia tasks such as search, retrieval and captioning. Unfortunately, these tasks are still challenging…”
Get full text

Nougat: Neural Optical Understanding for Academic Documents by Blecher, Lukas, Cucurull, Guillem, Scialom, Thomas, Stojnic, Robert

“…Scientific knowledge is predominantly stored in books and scientific journals, often in the form of PDFs. However, the PDF format leads to a loss of semantic…”
Get full text

On the Iterative Refinement of Densely Connected Representation Levels for Semantic Segmentation by Casanova, Arantxa, Cucurull, Guillem, Drozdzal, Michal, Romero, Adriana, Bengio, Yoshua

“…State-of-the-art semantic segmentation approaches increase the receptive field of their models by using either a downsampling path composed of poolings/strided…”
Get full text

Context-Aware Visual Compatibility Prediction by Cucurull, Guillem, Taslakian, Perouz, Vazquez, David

“…How do we determine whether two or more clothing items are compatible or visually appealing? Part of the answer lies in understanding of visual aesthetics, and…”
Get full text

Galactica: A Large Language Model for Science by Taylor, Ross, Kardas, Marcin, Cucurull, Guillem, Scialom, Thomas, Hartshorn, Anthony, Saravia, Elvis, Poulton, Andrew, Kerkez, Viktor, Stojnic, Robert

“…Information overload is a major obstacle to scientific progress. The explosive growth in scientific literature and data has made it ever harder to discover…”
Get full text

On the iterative refinement of densely connected representation levels for semantic segmentation by Casanova, Arantxa, Cucurull, Guillem, Drozdzal, Michal, Romero, Adriana, Bengio, Yoshua

“…State-of-the-art semantic segmentation approaches increase the receptive field of their models by using either a downsampling path composed of poolings/strided…”
Get full text

Attend and Rectify: a Gated Attention Mechanism for Fine-Grained Recovery by Rodríguez, Pau, Gonfaus, Josep M, Cucurull, Guillem, Roca, F. Xavier, Gonzàlez, Jordi

“…We propose a novel attention mechanism to enhance Convolutional Neural Networks for fine-grained recognition. It learns to attend to lower-level feature…”
Get full text

Llama 2: Open Foundation and Fine-Tuned Chat Models by Touvron, Hugo, Martin, Louis, Stone, Kevin, Albert, Peter, Almahairi, Amjad, Babaei, Yasmine, Bashlykov, Nikolay, Batra, Soumya, Bhargava, Prajjwal, Bhosale, Shruti, Bikel, Dan, Blecher, Lukas, Ferrer, Cristian Canton, Chen, Moya, Cucurull, Guillem, Esiobu, David, Fernandes, Jude, Fu, Jeremy, Fu, Wenyin, Fuller, Brian, Gao, Cynthia, Goswami, Vedanuj, Goyal, Naman, Hartshorn, Anthony, Hosseini, Saghar, Hou, Rui, Inan, Hakan, Kardas, Marcin, Kerkez, Viktor, Khabsa, Madian, Kloumann, Isabel, Korenev, Artem, Koura, Punit Singh, Lachaux, Marie-Anne, Lavril, Thibaut, Lee, Jenya, Liskovich, Diana, Lu, Yinghai, Mao, Yuning, Martinet, Xavier, Mihaylov, Todor, Mishra, Pushkar, Molybog, Igor, Nie, Yixin, Poulton, Andrew, Reizenstein, Jeremy, Rungta, Rashi, Saladi, Kalyan, Schelten, Alan, Silva, Ruan, Smith, Eric Michael, Subramanian, Ranjan, Tan, Xiaoqing Ellen, Tang, Binh, Taylor, Ross, Williams, Adina, Kuan, Jian Xiang, Xu, Puxin, Yan, Zheng, Zarov, Iliyan, Zhang, Yuchen, Fan, Angela, Kambadur, Melanie, Narang, Sharan, Rodriguez, Aurelien, Stojnic, Robert, Edunov, Sergey, Scialom, Thomas

“…In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70…”
Get full text

Deep Inference of Personality Traits by Integrating Image and Word Use in Social Networks by Cucurull, Guillem, Rodríguez, Pau, Yazici, V. Oguz, Gonfaus, Josep M, Roca, F. Xavier, Gonzàlez, Jordi

“…Social media, as a major platform for communication and information exchange, is a rich repository of the opinions and sentiments of 2.3 billion users about a…”
Get full text

Graph Attention Networks by Veličković, Petar, Cucurull, Guillem, Casanova, Arantxa, Romero, Adriana, Liò, Pietro, Bengio, Yoshua

“…We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers…”
Get full text

Regularizing CNNs with Locally Constrained Decorrelations by Rodríguez, Pau, Gonzàlez, Jordi, Cucurull, Guillem, Gonfaus, Josep M, Roca, Xavier

“…Regularization is key for deep learning since it allows training more complex models while keeping lower levels of overfitting. However, the most prevalent…”
Get full text