Search Results for author:
Found 50 papers, 28 papers with code
Polar Prototype Networks
The structure is defined by polar prototypes, points on the hypersphere of the output space.
Adversarial Attacks on Hyperbolic Networks
As hyperbolic deep learning grows in popularity, so does the need for adversarial robustness in the context of such a non-Euclidean geometry.
Maximally Separated Active Learning
Traditional uncertainty sampling often leads to sampling bias by choosing similar uncertain samples.
Compositional Entailment Learning for Hyperbolic Vision-Language Models
We show how to hierarchically organize images, image boxes, and their textual descriptions through contrastive and entailment-based objectives.
Lightweight Uncertainty Quantification with Simplex Semantic Segmentation for Terrain Traversability
We demonstrate the effectiveness of our module for terrain segmentation.
Hyp2Nav: Hyperbolic Planning and Curiosity for Crowd Navigation
Autonomous robots are increasingly becoming a strong fixture in social environments.
Find the Cliffhanger: Multi-Modal Trailerness in Soap Operas
Creating a trailer requires carefully picking out and piecing together brief enticing moments out of a longer video, making it a chal- lenging and time-consuming task.
Latent Space Editing in Transformer-Based Flow Matching
Flow Matching is an emerging generative modeling technique that offers the advantage of simple and efficient training.
Motion Flow Matching for Human Motion Synthesis and Editing
In this paper, we propose \emph{Motion Flow Matching}, a novel generative model designed for human motion generation featuring efficient sampling and effectiveness in motion editing applications.
Revisiting Proposal-based Object Detection
For proposal regression, we solve a simpler problem where we regress to the area of intersection between proposal and ground truth.
Query by Activity Video in the Wild
In this paper, we propose a visual-semantic embedding network that explicitly deals with the imbalanced scenario for activity retrieval.
Hyperbolic Random Forests
To make hyperbolic random forests work on multi-class data and imbalanced experiments, we furthermore outline a new method for combining classes based on their lowest common ancestor and a class-balanced version of the large-margin loss.
Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation
This paper investigates the problem of scene graph generation in videos with the aim of capturing semantic relations between subjects and objects in the form of $\langle$subject, predicate, object$\rangle$ triplets.
HypLL: The Hyperbolic Learning Library
Deep learning in hyperbolic space is quickly gaining traction in the fields of machine learning, multimedia, and computer vision.
Focus for Free in Density-Based Counting
Where density-based counting methods typically use the point annotations only to create Gaussian-density maps, which act as the supervision signal, the starting point of this work is that point annotations have counting potential beyond density map generation.
Infinite Class Mixup
To make optimisation tractable, we propose a dual-contrastive Infinite Class Mixup loss, where we contrast the classifier of a mixed pair to both the classifiers and the predicted outputs of other mixed pairs in a batch.
Hyperbolic Deep Learning in Computer Vision: A Survey
In this paper, we provide a categorization and in-depth overview of current literature on hyperbolic learning for computer vision.
Poincaré ResNet
This paper introduces an end-to-end residual network that operates entirely on the Poincar\'e ball model of hyperbolic space.
Poincare ResNet
(iii) Due to the many intermediate operations in Poincare layers, the computation graphs of deep learning libraries blow up, limiting our ability to train on deep hyperbolic networks.
Multi-Task Edge Prediction in Temporally-Dynamic Video Graphs
In such temporally-dynamic graphs, a core problem is inferring the future state of spatio-temporal edges, which can constitute multiple types of relations.
Self-Contained Entity Discovery from Captioned Videos
This paper introduces the task of visual named entity discovery in videos without the need for task-specific supervision or task-specific external knowledge sources.
Maximum Class Separation as Inductive Bias in One Matrix
This paper proposes a simple alternative: encoding maximum separation as an inductive bias in the network by adding one fixed matrix multiplication before computing the softmax activations.
Less than Few: Self-Shot Video Instance Segmentation
The goal of this paper is to bypass the need for labelled examples in few-shot video understanding at run time.
Hyperbolic Image Segmentation
For image segmentation, the current standard is to perform pixel-level optimization and inference in Euclidean output embedding spaces through linear hyperplanes.
Universal Prototype Transport for Zero-Shot Action Recognition and Localization
For universal object models, we outline a variant that defines target prototypes based on an optimal transport between unseen action prototypes and object prototypes.
Zero-Shot Action Recognition from Diverse Object-Scene Compositions
This paper investigates the problem of zero-shot action recognition, in the setting where no training videos with seen actions are available.
Diagnosing Errors in Video Relation Detectors
Video relation detection forms a new and challenging problem in computer vision, where subjects and objects need to be localized spatio-temporally and a predicate label needs to be assigned if and only if there is an interaction between the two.
Transductive Universal Transport for Zero-Shot Action Recognition
For universal object models, we outline a weighted transport variant from unseen action embeddings to object embeddings directly.
Social Fabric: Tubelet Compositions for Video Relation Detection
We also propose Social Fabric: an encoding that represents a pair of object tubelets as a composition of interaction primitives.
Ranked #1 on
Video Visual Relation Detection
on VidOR
Frequency-Supervised MR-to-CT Image Synthesis
In this paper, we find that all existing approaches share a common limitation: reconstruction breaks down in and around the high-frequency parts of CT images.
On Measuring and Controlling the Spectral Bias of the Deep Image Prior
The deep image prior showed that a randomly initialized network with a suitable architecture can be trained to solve inverse imaging problems by simply optimizing it's parameters to reconstruct a single degraded image.
Hyperbolic Busemann Learning with Ideal Prototypes
To be able to compute proximities to ideal prototypes, we introduce the penalised Busemann loss.
Unsharp Mask Guided Filtering
The state-of-the-art leverages deep networks to estimate the two core coefficients of the guided filter.
Object Priors for Classifying and Localizing Unseen Actions
This work strives for the classification and localization of human actions in videos, without the need for any labeled video training examples.
Few-Shot Transformation of Common Actions into Time and Space
This paper introduces the task of few-shot common action localization in time and space.
Adversarial Self-Supervised Scene Flow Estimation
This work proposes a metric learning approach for self-supervised scene flow estimation.
PointMixup: Augmentation for Point Clouds
In this paper, we define data augmentation between point clouds as a shortest path linear interpolation.
Ranked #3 on
3D Point Cloud Data Augmentation
on ModelNet40
3D Point Cloud Classification
3D Point Cloud Data Augmentation
+2
Localizing the Common Action Among a Few Videos
The start and end of an action in a long untrimmed video is determined based on just a hand-full of trimmed video examples containing the same action, without knowing their common class label.
Open Cross-Domain Visual Search
In this paper, we make the step towards an open setting where multiple visual domains are available.
4-Connected Shift Residual Networks
Interestingly, when incorporating shifts to all point-wise convolutions in residual networks, 4-connected shifts outperform 8-connected shifts.
Counting with Focus for Free
To assist both the density estimation and the focus from segmentation, we also introduce an improved kernel size estimator for the point annotations.
Hyperspherical Prototype Networks
This paper introduces hyperspherical prototype networks, which unify classification and regression with prototypes on hyperspherical output spaces.
Spatio-Temporal Instance Learning: Action Tubes from Class Supervision
Rather than disconnecting the spatio-temporal learning from the training, we propose Spatio-Temporal Instance Learning, which enables action localization directly from box proposals in video frames.
Multiple Instance Learning
Spatio-Temporal Action Localization
+1
Pointly-Supervised Action Localization
Experimental evaluation on three action localization datasets shows our pointly-supervised approach (i) is as effective as traditional box-supervision at a fraction of the annotation cost, (ii) is robust to sparse and noisy point annotations, (iii) benefits from pseudo-points during inference, and (iv) outperforms recent weakly-supervised alternatives.
Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions
Action localization and classification experiments on four contemporary action video datasets support our proposal.
Localizing Actions from Video Labels and Pseudo-Annotations
The goal of this paper is to determine the spatio-temporal location of actions in video.
Spot On: Action Localization from Pointly-Supervised Proposals
Rather than annotating boxes, we propose to annotate actions in video with points on a sparse subset of frames only.
The ImageNet Shuffle: Reorganized Pre-training for Video Event Detection
To deal with the problems of over-specific classes and classes with few images, we introduce a bottom-up and top-down approach for reorganization of the ImageNet hierarchy based on all its 21, 814 classes and more than 14 million images.
Water Detection through Spatio-Temporal Invariant Descriptors
Experimental evaluation on the Video Water Database and the DynTex database indicates the effectiveness of the proposed algorithm, outperforming multiple algorithms for dynamic texture recognition and material recognition by ca.
No Spare Parts: Sharing Part Detectors for Image Categorization
This work aims for image categorization using a representation of distinctive parts.
