92 citations · 195 across the 13 of their papers we have counts for
15 papers
Model Casting and Low-Parameter Gating: Towards More Sparsely Activated FFNs
Maria Lomeli, Antoine Groudiev, Matthijs Douze +7
This paper introduces model casting, a mid-training recipe that drastically sparsifies the activations within the Feed-Forward Network (FFN) layer. With this strategy, at inference…
Beyond Language Modeling: An Exploration of Multimodal Pretraining
Shengbang Tong, David Fan, John Nguyen +18
The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models r…
Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation
Dahyun Kang, Piotr Koniusz, Minsu Cho +1
We address the task of weakly-supervised few-shot image classification and segmentation, by leveraging a Vision Transformer (ViT) pretrained with self-supervision. Our proposed met…
Dungeons and Data: A Large-Scale NetHack Dataset
Eric Hambro, Roberta Raileanu, Danielle Rothermel +4
Recent breakthroughs in the development of agents to solve challenging sequential decision making problems such as Go, StarCraft, or DOTA, have relied on both simulated environment…
Time-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detection
Shan Zhang, Naila Murray, Lei Wang +1
In this paper, we tackle the challenging problem of Few-shot Object Detection. Existing FSOD pipelines (i) use average-pooled representations that result in information loss; and/o…
Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation
M. Saquib Sarfraz, Naila Murray, Vivek Sharma +3
Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos and is an important requirement for many video understanding tasks. For this…
Virtual KITTI 2
Yohann Cabon, Naila Murray, Martin Humenberger
This paper introduces an updated version of the well-known Virtual KITTI dataset which consists of 5 sequence clones from the KITTI tracking benchmark. In addition, the dataset pro…
Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models
César Roberto de Souza, Adrien Gaidon, Yohann Cabon +2
Deep video action recognition models have been highly successful in recent years but require large quantities of manually annotated data, which are expensive and laborious to obtai…
End-to-End Saliency Mapping via Probability Distribution Prediction
Saumya Jetley, Naila Murray, Eleonora Vig
Most saliency estimation methods aim to explicitly model low-level conspicuity cues such as edges or blobs and may additionally incorporate top-down cues using face or text detecti…
Re-ID done right: towards good practices for person re-identification
Jon Almazan, Bojana Gajic, Naila Murray +1
Training a deep architecture using a ranking loss has become standard for the person re-identification task. Increasingly, these deep architectures include additional components th…
A deep architecture for unified aesthetic prediction
Naila Murray, Albert Gordo
Image aesthetics has become an important criterion for visual content curation on social media sites and media content repositories. Previous work on aesthetic prediction models in…
Interferences in match kernels
Naila Murray, Hervé Jégou, Florent Perronnin +1
We consider the design of an image representation that embeds and aggregates a set of local descriptors into a single vector. Popular representations of this kind include the bag-o…
LEWIS: Latent Embeddings for Word Images and their Semantics
Albert Gordo, Jon Almazan, Naila Murray +1
The goal of this work is to bring semantics into the tasks of text recognition and retrieval in natural images. Although text recognition and retrieval have received a lot of atten…
Discovering beautiful attributes for aesthetic image analysis
Luca Marchesotti, Naila Murray, Florent Perronnin
Aesthetic image analysis is the study and assessment of the aesthetic properties of images. Current computational approaches to aesthetic image analysis either provide accurate or…
Generalized Max Pooling
Naila Murray, Florent Perronnin
State-of-the-art patch-based image representations involve a pooling operation that aggregates statistics computed from local descriptors. Standard pooling operations include sum-…