Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

/pdf/deep-residual-learning-for-image-recognition-b75jg61qrq.pdf

Deep Residual Learning for Image Recognition

In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. 
The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

We present a method for mining frequently occurring objects and scenes from videos. Object candidates are detected by finding recurring spatial arrangements of affine covariant regions. Our mining method is based on the class of frequent itemset mining algorithms, which have proven their efficiency in other domains, but have not been applied to video mining before. In this work we show how to express vector-quantized features and their spatial relations as itemsets. Furthermore, a fast motion segmentation method is introduced as an attention filter for the mining algorithm. Results are shown on real world data consisting of music video clips.

/pdf/video-mining-with-frequent-itemset-configurations-17xikp6u0k.pdf

Video mining with frequent itemset configurations

Progress in Multiple Object Tracking (MOT) has been historically limited by the size of the available datasets. We present an efficient framework to annotate trajectories and use it to produce a MOT dataset of unprecedented size. In our novel path supervision the annotator loosely follows the object with the cursor while watching the video, providing a path annotation for each object in the sequence. Our approach is able to turn such weak annotations into dense box trajectories. Our experiments on existing datasets prove that our framework produces more accurate annotations than the state of the art, in a fraction of the time. We further validate our approach by crowdsourcing the PathTrack dataset, with more than 15,000 person trajectories in 720 sequences. Tracking approaches can benefit training on such large-scale datasets, as did object recognition. We prove this by re-training an off-the-shelf person matching network, originally trained on the MOT15 dataset, almost halving the misclassification rate. Additionally, training on our data consistently improves tracking results, both on our dataset and on MOT15. On the latter, we improve the top-performing tracker (NOMT) dropping the number of ID Switches by 18% and fragments by 5%.

/pdf/pathtrack-fast-trajectory-annotation-with-path-supervision-4ek6h5urbt.pdf

PathTrack: Fast Trajectory Annotation with Path Supervision

The video and action classification have extremely evolved by deep neural networks specially with two stream CNN using RGB and optical flow as inputs and they present outstanding performance in terms of video analysis. One of the shortcoming of these methods is handling motion information extraction which is done out side of the CNNs and relatively time consuming also on GPUs. So proposing end-to-end methods which are exploring to learn motion representation, like 3D-CNN can achieve faster and accurate performance. We present some novel deep CNNs using 3D architecture to model actions and motion representation in an efficient way to be accurate and also as fast as real-time. Our new networks learn distinctive models to combine deep motion features into appearance model via learning optical flow features inside the network.

Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification

3D human pose estimation in multi-view settings benefits from embeddings of human actions in low-dimensional manifolds, but the complexity of the embeddings increases with the number of actions. Creating separate, action-specific manifolds seems to be a more practical solution. Using multiple manifolds for pose estimation, however, requires a joint optimization over the set of manifolds and the human pose embedded in the manifolds. In order to solve this problem, we propose a particle-based optimization algorithm that can efficiently estimate human pose even in challenging in-house scenarios. In addition, the algorithm can directly integrate the results of a 2D action recognition system as prior distribution for optimization. In our experiments, we demonstrate that the optimization handles an 84D search space and provides already competitive results on HumanEva with as few as 25 particles.

/pdf/2d-action-recognition-serves-3d-human-pose-estimation-260qqdmftq.pdf

2D action recognition serves 3D human pose estimation

Cross-domain mapping has been a very active topic in recent years. Given one image, its main purpose is to translate it to the desired target domain, or multiple domains in the case of multiple labels. This problem is highly challenging due to three main reasons: (i) unpaired datasets, (ii) multiple attributes, and (iii) the multimodality (e.g. style) associated with the translation. Most of the existing state-of-the-art has focused only on two reasons i.e., either on (i) and (ii) or (i) and (iii). In this work, we propose a joint framework (i, ii, iii) of diversity and multi-mapping image-to-image translations, using a single generator to conditionally produce countless and unique fake images that hold the underlying characteristics of the source image. Our system does not use style regularization, instead, it uses an embedding representation that we call domain embedding for both domain and style. Extensive experiments over different datasets demonstrate the effectiveness of our proposed approach in comparison with the state-of-the-art in both multi-label and multimodal problems. Additionally, our method is able to generalize under different scenarios: continuous style interpolation, continuous label interpolation, and fine-grained mapping.

/pdf/smit-stochastic-multi-label-image-to-image-translation-18c8ee46oj.pdf

Luc Van Gool

Papers

Video mining with frequent itemset configurations

PathTrack: Fast Trajectory Annotation with Path Supervision

Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification

2D action recognition serves 3D human pose estimation

SMIT: Stochastic Multi-Label Image-to-Image Translation