Thomas Serre

Robust Object Recognition with Cortex-Like Mechanisms

We introduce a new general framework for the recognition of complex visual scenes, which is motivated by biology: We describe a hierarchical system that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature representation by alternating between a template matching and a maximum pooling operation. We demonstrate the strength of the approach on a range of recognition tasks: From invariant single object recognition in clutter to multiclass categorization problems and complex scene understanding tasks that rely on the recognition of both shape-based as well as texture-based objects. Given the biological constraints that the system had to satisfy, the approach performs surprisingly well: It has the capability of learning from only a few training examples and competes with state-of-the-art systems. We also discuss the existence of a universal, redundant dictionary of features that could handle the recognition of most object categories. In addition to its relevance for computer vision, the success of this approach suggests a plausibility proof for a class of feedforward models of object recognition in cortex

HMDB: A large video database for human motion recognition

With nearly one billion online videos viewed everyday, an emerging new frontier in computer vision research is recognition and search in video. While much effort has been devoted to the collection and annotation of large scalable static image datasets containing thousands of image categories, human action datasets lag far behind. Current action recognition databases contain on the order of ten different action categories collected under fairly controlled conditions. State-of-the-art performance on these datasets is now near ceiling and thus there is a need for the design and creation of new benchmarks. To address this issue we collected the largest action video database to-date with 51 action categories, which in total contain around 7,000 manually annotated clips extracted from a variety of sources ranging from digitized movies to YouTube. We use this database to evaluate the performance of two representative computer vision systems for action recognition and explore the robustness of these methods under various conditions such as camera motion, viewpoint, video quality and occlusion.

Object recognition with features inspired by visual cortex

We introduce a novel set of features for robust object recognition. Each element of this set is a complex feature obtained by combining position- and scale-tolerant edge-detectors over neighboring positions and multiple orientations. Our systems architecture is motivated by a quantitative model of visual cortex. We show that our approach exhibits excellent recognition performance and outperforms several state-of-the-art systems on a variety of image datasets including many different object categories. We also demonstrate that our system is able to learn from very few examples. The performance of the approach constitutes a suggestive plausibility proof for a class of feedforward models of object recognition in cortex.

A feedforward architecture accounts for rapid categorization

Primates are remarkably good at recognizing objects. The level of performance of their visual system and its robustness to image degradations still surpasses the best computer vision systems despite decades of engineering effort. In particular, the high accuracy of primates in ultra rapid object categorization and rapid serial visual presentation tasks is remarkable. Given the number of processing stages involved and typical neural latencies, such rapid visual processing is likely to be mostly feedforward. Here we show that a specific implementation of a class of feedforward theories of object recognition (that extend the Hubel and Wiesel simple-to-complex cell hierarchy and account for many anatomical and physiological constraints) can predict the level and the pattern of performance achieved by humans on a rapid masked animal vs. non-animal categorization task.

A Biologically Inspired System for Action Recognition

We present a biologically-motivated system for the recognition of actions from video sequences. The approach builds on recent work on object recognition based on hierarchical feedforward architectures [25, 16, 20] and extends a neurobiological model of motion processing in the visual cortex [10]. The system consists of a hierarchy of spatio-temporal feature detectors of increasing complexity: an input sequence is first analyzed by an array of motion- direction sensitive units which, through a hierarchy of processing stages, lead to position-invariant spatio-temporal feature detectors. We experiment with different types of motion-direction sensitive units as well as different system architectures. As in [16], we find that sparse features in intermediate stages outperform dense ones and that using a simple feature selection approach leads to an efficient system that performs better with far fewer features. We test the approach on different publicly available action datasets, in all cases achieving the highest results reported to date.

Hierarchical classification and feature reduction for fast face detection with support vector machines

We present a two-step method to speed-up object detection systems in computer vision that use support vector machines as classifiers. In the first step we build a hierarchy of classifiers. On the bottom level, a simple and fast linear classifier analyzes the whole image and rejects large parts of the background. On the top level, a slower but more accurate classifier performs the final detection. We propose a new method for automatically building and training a hierarchy of classifiers. In the second step we apply feature reduction to the top level classifier by choosing relevant image features according to a measure derived from statistical learning theory. Experiments with a face detection system show that combining feature reduction with hierarchical classification leads to a speed-up by a factor of 335 with similar classification performance.

A Component-based Framework for Face Detection and Identification

We present a component-based framework for face detection and identification. The face detection and identification modules share the same hierarchical architecture. They both consist of two layers of classifiers, a layer with a set of component classifiers and a layer with a single combination classifier. The component classifiers independently detect/identify facial parts in the image. Their outputs are passed the combination classifier which performs the final detection/identification of the face.We describe an algorithm which automatically learns two separate sets of facial components for the detection and identification tasks. In experiments we compare the detection and identification systems to standard global approaches. The experimental results clearly show that our component-based approach is superior to global approaches.

Component-based face detection

We present a component-based, trainable system for detecting frontal and near-frontal views of faces in still gray images. The system consists of a two-level hierarchy of Support Vector Machine (SVM) classifiers. On the first level, component classifiers independently detect components Of a face. On the second level, a single classifier checks if the geometrical configuration of the detected components in the image matches a geometrical model of a face. We propose a method for automatically learning components by using 3-D head models, This approach has the advantage that no manual interaction is required for choosing and extracting components. Experiments show that the component-based system is significantly more robust against rotations in depth than a comparable system trained on whole face patterns.

A quantitative theory of immediate visual recognition.

Human and non-human primates excel at visual recognition tasks. The primate visual system exhibits a strong degree of selectivity while at the same time being robust to changes in the input image. We have developed a quantitative theory to account for the computations performed by the feedforward path in the ventral stream of the primate visual cortex. Here we review recent predictions by a model instantiating the theory about physiological observations in higher visual areas. We also show that the model can perform recognition tasks on datasets of complex natural images at a level comparable to psychophysical measurements on human observers during rapid categorization tasks. In sum, the evidence suggests that the theory may provide a framework to explain the first 100-150 ms of visual object recognition. The model also constitutes a vivid example of how computational models can interact with experimental observations in order to advance our understanding of a complex phenomenon. We conclude by suggesting a number of open questions, predictions, and specific experiments for visual physiology and psychophysics.

What and where: A Bayesian inference theory of attention

In the theoretical framework of this paper, attention is part of the inference process that solves the visual recognition problem of what is where. The theory proposes a computational role for attention and leads to a model that predicts some of its main properties at the level of psychophysics and physiology. In our approach, the main goal of the visual system is to infer the identity and the position of objects in visual scenes: spatial attention emerges as a strategy to reduce the uncertainty in shape information while feature-based attention reduces the uncertainty in spatial information. Featural and spatial attention represent two distinct modes of a computational process solving the problem of recognizing and localizing objects, especially in difficult recognition tasks such as in cluttered natural scenes. We describe a specific computational model and relate it to the known functional anatomy of attention. We show that several well-known attentional phenomena--including bottom-up pop-out effects, multiplicative modulation of neuronal tuning curves and shift in contrast responses--all emerge naturally as predictions of the model. We also show that the Bayesian model predicts well human eye fixations (considered as a proxy for shifts of attention) in natural scenes.