Search Results for author: Arnold W. M. Smeulders

Found 28 papers, 5 papers with code

Structured Visual Search via Composition-aware Learning

no code implementations27 Oct 2020 Mert Kilickaya, Arnold W. M. Smeulders

The structure is in the form of a 2D composition that encodes the position and the category of the objects.


PIC: Permutation Invariant Convolution for Recognizing Long-range Activities

no code implementations18 Mar 2020 Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders

We study the three properties of PIC and demonstrate its effectiveness in recognizing the long-range activities of Charades, Breakfast, and MultiThumos.

Go with the Flow: Perception-refined Physics Simulation

no code implementations17 Oct 2019 Tom F. H. Runia, Kirill Gavrilyuk, Cees G. M. Snoek, Arnold W. M. Smeulders

Nevertheless, inferring specifics from visual observations is challenging due to the high number of causally underlying physical parameters -- including material properties and external forces.

Model Decay in Long-Term Tracking

no code implementations5 Aug 2019 Efstratios Gavves, Ran Tao, Deepak K. Gupta, Arnold W. M. Smeulders

Updating the tracker model with adverse bounding box predictions adds an unavoidable bias term to the learning.

Timeception for Complex Action Recognition

3 code implementations CVPR 2019 Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders

This paper focuses on the temporal aspect for recognizing human activities in videos; an important visual cue that has long been undervalued.

Action Classification Action Recognition +2

Estimating Small Differences in Car-Pose from Orbits

no code implementations3 Sep 2018 Berkay Kicanaoglu, Ran Tao, Arnold W. M. Smeulders

The generated orbit in the latent space records all the differences in pose in the original observational space, and as a result, the method is capable of finding subtle differences in pose.


Repetition Estimation

1 code implementation18 Jun 2018 Tom F. H. Runia, Cees G. M. Snoek, Arnold W. M. Smeulders

Estimating visual repetition from realistic video is challenging as periodic motion is rarely perfectly static and stationary.

Asymmetric kernel in Gaussian Processes for learning target variance

no code implementations19 Mar 2018 Silvia L. Pintea, Jan C. van Gemert, Arnold W. M. Smeulders

This enables each center to adjust the kernel space in its vicinity in correspondence with the topology of the targets --- a multi-modal approach.

Gaussian Processes Metric Learning +1

Deja Vu: Motion Prediction in Static Images

1 code implementation19 Mar 2018 Silvia L. Pintea, Jan C. van Gemert, Arnold W. M. Smeulders

This paper proposes motion prediction in single still images by learning it from a set of videos.

Action Recognition motion prediction +2

Real-World Repetition Estimation by Div, Grad and Curl

no code implementations CVPR 2018 Tom F. H. Runia, Cees G. M. Snoek, Arnold W. M. Smeulders

We consider the problem of estimating repetition in video, such as performing push-ups, cutting a melon or playing violin.

Tracking for Half an Hour

1 code implementation28 Nov 2017 Ran Tao, Efstratios Gavves, Arnold W. M. Smeulders

Long-term tracking requires extreme stability to the multitude of model updates and robustness to the disappearance and loss of the target as such will inevitably happen.

Dynamic Steerable Blocks in Deep Residual Networks

no code implementations2 Jun 2017 Jörn-Henrik Jacobsen, Bert de Brabandere, Arnold W. M. Smeulders

Filters in convolutional networks are typically parameterized in a pixel basis, that does not take prior knowledge about the visual world into account.

Contour Detection

Multiscale Hierarchical Convolutional Networks

no code implementations12 Mar 2017 Jörn-Henrik Jacobsen, Edouard Oyallon, Stéphane Mallat, Arnold W. M. Smeulders

Multiscale hierarchical convolutional networks are structured deep convolutional networks where layers are indexed by progressively higher dimensional attributes, which are learned from training data.


Generating captions without looking beyond objects

no code implementations12 Oct 2016 Hendrik Heuer, Christof Monz, Arnold W. M. Smeulders

This paper explores new evaluation perspectives for image captioning and introduces a noun translation task that achieves comparative image caption generation performance by translating from a set of nouns to captions.

Caption Generation Image Captioning +2

Searching Scenes by Abstracting Things

no code implementations6 Oct 2016 Svetlana Kordumova, Jan C. van Gemert, Cees G. M. Snoek, Arnold W. M. Smeulders

Second, we propose translating the things syntax in linguistic abstract statements and study their descriptive effect to retrieve scenes.

Attribute Descriptive +1

Generic Instance Search and Re-identification from One Example via Attributes and Categories

no code implementations23 May 2016 Ran Tao, Arnold W. M. Smeulders, Shih-Fu Chang

Searching among instances from the same category as the query, the category-specific attributes outperform existing approaches by a large margin on shoes and cars and perform on par with the state-of-the-art on buildings.

Instance Search Person Re-Identification

Siamese Instance Search for Tracking

no code implementations CVPR 2016 Ran Tao, Efstratios Gavves, Arnold W. M. Smeulders

In this paper we present a tracker, which is radically different from state-of-the-art trackers: we apply no model updating, no occlusion detection, no combination of trackers, no geometric matching, and still deliver state-of-the-art tracking performance, as demonstrated on the popular online tracking benchmark (OTB) and six very challenging YouTube videos.

Geometric Matching Instance Search

Structured Receptive Fields in CNNs

3 code implementations CVPR 2016 Jörn-Henrik Jacobsen, Jan van Gemert, Zhongyu Lou, Arnold W. M. Smeulders

We combine these ideas into structured receptive field networks, a model which has a fixed filter basis and yet retains the flexibility of CNNs.

Attributes and Categories for Generic Instance Search From One Example

no code implementations CVPR 2015 Ran Tao, Arnold W. M. Smeulders, Shih-Fu Chang

This paper aims for generic instance search from one example where the instance can be an arbitrary 3D object like shoes, not just near-planar and one-sided instances like buildings and logos.

Instance Search

Fisher and VLAD with FLAIR

no code implementations CVPR 2014 Koen E. A. van de Sande, Cees G. M. Snoek, Arnold W. M. Smeulders

Finally, by multiple codeword assignments, we achieve exact and approximate Fisher vectors with FLAIR.

Cannot find the paper you are looking for? You can Submit a new open access paper.