https://vaquero.me/atom.xml New papers from Lorenzo Vaquero on computer vision, multi-object tracking, human–object interaction, vision–language models, and AI explainability. 2026-01-01T00:00:00.000Z Lorenzo Vaquero Otal https://vaquero.me/ https://vaquero.me/publications/2026-cvpr-from-weights-to-concepts/ 2026-01-01T00:00:00.000Z 2026-01-01T00:00:00.000Z

A data-free, training-free framework that directly analyses CLIP's vision transformer in weight space, decomposing each attention head into singular vectors linked to textual concepts. (IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026)

Francesco Gentile Nicola Dall'Asen Francesco Tonini Massimiliano Mancini Lorenzo Vaquero Elisa Ricci https://vaquero.me/publications/2026-perconai-efficient-portrait-segmentation-embedded-devices/ 2026-01-01T00:00:00.000Z 2026-01-01T00:00:00.000Z

SINergy is a scalable portrait segmentation network designed around embedded hardware constraints, reaching real-time segmentation on microcontroller-scale devices. (IEEE International Conference on Pervasive Computing and Communications Workshops, 2026)

Riccardo Benevelli Alberto Ancilotto Lorenzo Vaquero Elisa Ricci Elisabetta Farella https://vaquero.me/publications/2026-acmmm-finehoi/ 2026-01-01T00:00:00.000Z 2026-01-01T00:00:00.000Z

FineHOI detects unseen human-object interactions by reasoning over dense, part-level visual cues, improving fine-grained recognition without LLM or detector features. (ACM International Conference on Multimedia, 2026)

Francesco Tonini Lorenzo Vaquero Mohammad Mahdi Derakhshani Cees G. M. Snoek Elisa Ricci Cigdem Beyan https://vaquero.me/publications/2026-nature-humanitys-last-exam/ 2026-01-01T00:00:00.000Z 2026-01-01T00:00:00.000Z

Humanity's Last Exam is a multimodal benchmark of 2,500 expert-level closed-ended academic questions designed to measure frontier AI capabilities beyond saturated benchmarks. (Nature, 2026)

Center for AI Safety Scale AI HLE Contributors Consortium https://vaquero.me/publications/2026-caepia-keynote-lost-and-found/ 2026-01-01T00:00:00.000Z 2026-01-01T00:00:00.000Z

This keynote paper summarizes BUSCA, a work published in ECCV'24. BUSCA plugs into online tracking-by-detection systems to recover objects missed by detectors through proposal generation and decision-transformer association. (Conference of the Spanish Association for Artificial Intelligence, 2026)

Lorenzo Vaquero Yihong Xu Xavier Alameda-Pineda Víctor M. Brea Manuel Mucientes https://vaquero.me/publications/2026-caepia-keynote-superpowering-open-vocabulary-object-detectors-x-ray-vision/ 2026-01-01T00:00:00.000Z 2026-01-01T00:00:00.000Z

This keynote paper summarizes RAXO, a work published in ICCV'25. RAXO adapts RGB open-vocabulary detectors to X-ray imagery with training-free visual descriptors and introduces DET-COMPASS for large-scale X-ray OvOD evaluation. (Conference of the Spanish Association for Artificial Intelligence, 2026)

Pablo Garcia-Fernandez Lorenzo Vaquero Mingxuan Liu Feng Xue Daniel Cores Nicu Sebe Manuel Mucientes Elisa Ricci https://vaquero.me/publications/2026-fg-towards-unconstrained-human-object-interaction/ 2026-01-01T00:00:00.000Z 2026-01-01T00:00:00.000Z

AnyHOI studies human-object interaction detection without a predefined interaction vocabulary, using multimodal LLMs and language-to-graph conversion to recover structured triplets from free-form outputs. (IEEE International Conference on Automatic Face and Gesture Recognition, 2026)

Francesco Tonini Alessandro Conti Lorenzo Vaquero Cigdem Beyan Elisa Ricci https://vaquero.me/publications/2026-fg-training-free-semantic-multi-object-tracking/ 2026-01-01T00:00:00.000Z 2026-01-01T00:00:00.000Z

TF-SMOT composes frozen detection, segmentation tracking, video-language generation, and LLM disambiguation modules to produce semantic tracking outputs without task-specific training. (IEEE International Conference on Automatic Face and Gesture Recognition, 2026)

Laurence Bonat Francesco Tonini Elisa Ricci Lorenzo Vaquero https://vaquero.me/publications/2026-fg-zero-shot-temporal-action-localization/ 2026-01-01T00:00:00.000Z 2026-01-01T00:00:00.000Z

TeGu compensates for the lack of supervision in zero-shot temporal action localization by exploiting rich textual cues from large language models, distinguishing foreground from background frames without training. (IEEE International Conference on Automatic Face and Gesture Recognition, 2026)

Benedetta Liberatori Alessandro Conti Lorenzo Vaquero Paolo Rota Yiming Wang Elisa Ricci https://vaquero.me/publications/2025-neurips-convis-bench/ 2025-01-01T00:00:00.000Z 2025-01-01T00:00:00.000Z

ConViS-Bench evaluates video similarity along semantic concepts, pairing concept-level human scores with free-form descriptions for interpretable video comparison. (Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2025)

Benedetta Liberatori Alessandro Conti Lorenzo Vaquero Yiming Wang Elisa Ricci Paolo Rota https://vaquero.me/publications/2025-acmmm-dynamic-scoring-hoi-detection/ 2025-01-01T00:00:00.000Z 2025-01-01T00:00:00.000Z

DYSCO is a training-free HOI detector that combines textual and visual interaction representations in a multimodal registry with dynamic multi-head scoring. (ACM International Conference on Multimedia, 2025)

Francesco Tonini Lorenzo Vaquero Alessandro Conti Cigdem Beyan Elisa Ricci https://vaquero.me/publications/2025-ibpria-enhancing-multi-object-tracking-segmentation-masks/ 2025-01-01T00:00:00.000Z 2025-01-01T00:00:00.000Z

A lost-track recovery architecture uses segmentation masks and a transformer-based mask selector to preserve tracks when detectors fail in crowded scenes. (Iberian Conference on Pattern Recognition and Image Analysis, 2025)

Manuel Bendaña Lorenzo Vaquero Víctor M. Brea Manuel Mucientes https://vaquero.me/publications/2025-iccv-superpowering-open-vocabulary-object-detectors-x-ray-vision/ 2025-01-01T00:00:00.000Z 2025-01-01T00:00:00.000Z

RAXO adapts RGB open-vocabulary detectors to X-ray imagery with training-free visual descriptors and introduces DET-COMPASS for large-scale X-ray OvOD evaluation. (IEEE/CVF International Conference on Computer Vision, 2025)

Pablo Garcia-Fernandez Lorenzo Vaquero Mingxuan Liu Feng Xue Daniel Cores Nicu Sebe Manuel Mucientes Elisa Ricci https://vaquero.me/publications/2024-eccv-lost-and-found/ 2024-01-01T00:00:00.000Z 2024-01-01T00:00:00.000Z

BUSCA plugs into online tracking-by-detection systems to recover objects missed by detectors through proposal generation and decision-transformer association. (European Conference on Computer Vision, 2024)

Lorenzo Vaquero Yihong Xu Xavier Alameda-Pineda Víctor M. Brea Manuel Mucientes https://vaquero.me/publications/2024-acmmm-al-gtd/ 2024-01-01T00:00:00.000Z 2024-01-01T00:00:00.000Z

AL-GTD reduces gaze target annotation cost by combining supervised and self-supervised signals in an active learning acquisition function with pseudo-labeling. (ACM International Conference on Multimedia, 2024)

Francesco Tonini Nicola Dall'Asen Lorenzo Vaquero Cigdem Beyan Elisa Ricci https://vaquero.me/publications/2024-iscas-live-demonstration-sram-dnn-cim/ 2024-01-01T00:00:00.000Z 2024-01-01T00:00:00.000Z

A live mixed-signal compute-in-memory demonstration uses 5-bit signed SRAM weights and PWM-coded images for low-power DNN image recognition. (IEEE International Symposium on Circuits and Systems, 2024)

Ó. Pereira-Rial D. García-Lesta Lorenzo Vaquero P. López Víctor M. Brea D. Cabello https://vaquero.me/publications/2023-pattern-recognition-real-time-siamese-multiple-object-tracker/ 2023-01-01T00:00:00.000Z 2023-01-01T00:00:00.000Z

SiamMOTION tracks dozens of arbitrary objects in real time through feature-pyramid proposals, attention, inertia, pairwise depthwise RPN matching, and multi-object penalization. (Pattern Recognition, 2023)

Lorenzo Vaquero Víctor M. Brea Manuel Mucientes https://vaquero.me/publications/2023-tci-depth-estimation-image-restoration-defocused-images/ 2023-01-01T00:00:00.000Z 2023-01-01T00:00:00.000Z

2HDED:NET jointly estimates depth and restores all-in-focus images from defocused input through a shared encoder and parallel task branches. (IEEE Transactions on Computational Imaging, 2023)

Saqib Nazir Lorenzo Vaquero Manuel Mucientes Víctor M. Brea Daniela Coltuc https://vaquero.me/publications/2022-icip-2hded-net/ 2022-01-01T00:00:00.000Z 2022-01-01T00:00:00.000Z

2HDED:NET performs depth-from-defocus and all-in-focus image restoration in parallel through a shared encoder and two balanced decoder branches. (IEEE International Conference on Image Processing, 2022)

Saqib Nazir Lorenzo Vaquero Manuel Mucientes Víctor M. Brea Daniela Coltuc https://vaquero.me/publications/2022-icpr-fast-multi-object-tracking-feature-pyramid-region-proposal-networks/ 2022-01-01T00:00:00.000Z 2022-01-01T00:00:00.000Z

SiamFAST brings feature-pyramid ROI extraction, pairwise depthwise RPN matching, and multi-object penalization to real-time arbitrary multi-object tracking. (International Conference on Pattern Recognition, 2022)

Lorenzo Vaquero Víctor M. Brea Manuel Mucientes https://vaquero.me/publications/2021-pattern-recognition-tracking-more-than-100-arbitrary-objects/ 2021-01-01T00:00:00.000Z 2021-01-01T00:00:00.000Z

SiamMT scales visual object tracking to dozens of arbitrary objects by reusing feature computations and introducing efficient crop-resize and pairwise similarity operators. (Pattern Recognition, 2021)

Lorenzo Vaquero Víctor M. Brea Manuel Mucientes https://vaquero.me/publications/2020-icpr-siammt/ 2020-01-01T00:00:00.000Z 2020-01-01T00:00:00.000Z

SiamMT is a Siamese convolutional architecture for tracking multiple arbitrary objects in real time by sharing frame features and using pairwise cross-correlation. (International Conference on Pattern Recognition, 2020)

Lorenzo Vaquero Manuel Mucientes Víctor M. Brea https://vaquero.me/publications/2018-wgml-deep-learning-video-object-detection-tracking/ 2018-01-01T00:00:00.000Z 2018-01-01T00:00:00.000Z

Brief summary of deep convolutional approaches for small-object detection, real-time multi-object tracking, and integrated traffic monitoring. (Machine Learning Workshop Galicia, 2018)

Brais Bosquet Mauro Fernández-Sanjurjo Lorenzo Vaquero Daniel Cores Víctor M. Brea Manuel Mucientes