Search Results for author:
Found 37 papers, 21 papers with code
Deep Continuous Networks
CNNs and computational models of biological vision share some fundamental principles, which opened new avenues of research.
A step towards understanding why classification helps regression
A number of computer vision deep regression approaches report improved results when adding a classification loss to the regression loss.
Is there progress in activity progress prediction?
We conclude that the progress prediction task is ill-posed on the currently used real-world datasets.
Objects do not disappear: Video object detection by single-frame object location anticipation
2) Improved efficiency by only doing the expensive feature computations on a small subset of all frames.
Ranked #1 on
Video Object Detection
on Waymo Open Dataset
Differentiable Transportation Pruning
Deep learning algorithms are increasingly employed at the edge.
Evaluating Context for Deep Object Detectors
Which object detector is suitable for your context sensitive task?
Deep vanishing point detection: Geometric priors make dataset variations vanish
Deep learning has improved vanishing point detection in images.
Equal Bits: Enforcing Equally Distributed Binary Network Weights
We investigate experimentally that equal bit ratios are indeed preferable and show that our method leads to optimization benefits.
Frequency learning for structured CNN filters with Gaussian fractional derivatives
Frequency information lies at the base of discriminating between textures, and therefore between different objects.
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
In this work, we propose FlexConv, a novel convolutional operation with which high bandwidth convolutional kernels of learnable kernel size can be learned at a fixed parameter cost.
Investigating transformers in the decomposition of polygonal shapes as point collections
Transformers can generate predictions in two approaches: 1. auto-regressively by conditioning each sequence element on the previous ones, or 2. directly produce an output sequences in parallel.
Zero-Shot Day-Night Domain Adaptation with a Physics Prior
The traditional domain adaptation setting is to train on one domain and adapt to the target domain by exploiting unlabeled data samples from the test set.
Ranked #2 on
Image Retrieval
on 24/7 Tokyo
The Arm-Swing Is Discriminative in Video Gait Recognition for Athlete Re-Identification
In this paper we evaluate running gait as an attribute for video person re-identification in a long-distance running event.
Exploiting Learned Symmetries in Group Equivariant Convolutions
Group Equivariant Convolutions (GConvs) enable convolutional neural networks to be equivariant to various transformation groups, but at an additional parameter and compute cost.
Resolution learning in deep convolutional networks using scale-space theory
We use scale-space theory to obtain a self-similar parametrization of filters and make use of the N-Jet: a truncated Taylor series to approximate a filter by a learned combination of Gaussian derivative filters.
Hallucination In Object Detection -- A Study In Visual Part Verification
We show that object detectors can hallucinate and detect missing objects; potentially even accurately localized at their expected, but non-existing, position.
No frame left behind: Full Video Action Recognition
A common heuristic is uniformly sampling a small number of video frames and using these to recognize the action.
t-EVA: Time-Efficient t-SNE Video Annotation
Video understanding has received more attention in the past few years due to the availability of several large-scale video datasets.
Tilting at windmills: Data augmentation for deep pose estimation does not help with occlusions
Occlusion degrades the performance of human pose estimation.
Deep Hough-Transform Line Priors
Here, we reduce the dependency on labeled data by building on the classic knowledge-based priors while using deep networks to learn features.
Ranked #3 on
Line Segment Detection
on wireframe dataset
Top-Down Networks: A coarse-to-fine reimagination of CNNs
Biological vision adopts a coarse-to-fine information processing pathway, from initial visual detection and binding of salient features of a visual scene, to the enhanced and preferential processing given relevant stimuli.
On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location
In this paper we challenge the common assumption that convolutional layers in modern CNNs are translation invariant.
Cross Domain Image Matching in Presence of Outliers
Cross domain image matching between image collections from different source and target domains is challenging in times of deep learning due to i) limited variation of image conditions in a training set, ii) lack of paired-image labels during training, iii) the existing of outliers that makes image matching domains not fully overlap.
Hand-tremor frequency estimation in videos
We focus on the problem of estimating human hand-tremor frequency from input RGB video data.
Using phase instead of optical flow for action recognition
We design these complex filters to resemble complex Gabor filters, typically employed for phase-information extraction.
Recurrent knowledge distillation
Knowledge distillation compacts deep networks by letting a small student network learn from a large teacher network.
Deja Vu: Motion Prediction in Static Images
This paper proposes motion prediction in single still images by learning it from a set of videos.
Featureless: Bypassing feature extraction in action categorization
This method introduces an efficient manner of learning action categories without the need of feature estimation.
Asymmetric kernel in Gaussian Processes for learning target variance
This enables each center to adjust the kernel space in its vicinity in correspondence with the topology of the targets --- a multi-modal approach.
Video Acceleration Magnification
In these contexts there is often large motion present which severely distorts current video amplification methods that magnify change linearly.
Active Decision Boundary Annotation with Deep Generative Models
This paper is on active learning where the goal is to reduce the data annotation burden by interacting with a (human) oracle during training.
Searching Scenes by Abstracting Things
Second, we propose translating the things syntax in linguistic abstract statements and study their descriptive effect to retrieve scenes.
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.
Objects2action: Classifying and localizing actions without any video example
Our key contribution is objects2action, a semantic word embedding that is spanned by a skip-gram model of thousands of object categories.
Ranked #21 on
Zero-Shot Action Recognition
on UCF101
No Spare Parts: Sharing Part Detectors for Image Categorization
This work aims for image categorization using a representation of distinctive parts.
What do 15,000 Object Categories Tell Us About Classifying and Localizing Actions?
This paper contributes to automatic classification and localization of human actions in video.
Evaluation of Color STIPs for Human Action Recognition
Existing STIP-based action recognition approaches operate on intensity representations of the image data.
