arXiv subjects

Fabio Cuzzolin

Publications and source records attributed to Fabio Cuzzolin.

69 records · Page 4Linked to original sources

arXiv2018

Visions of a generalized probability theory

In this Book we argue that the fruitful interaction of computer vision and belief calculus is capable of stimulating significant advances in both fields. From a methodological point of view, novel theoretical results concerning the geometric and algebraic properties of belief functions as mathematical objects are illustrated and discussed in Part II, with a focus on both a perspective 'geometric approach' to uncertainty and an algebraic solution to the issue of conflicting evidence. In Part III we show how these theoretical developments arise from important computer vision problems (such as articulated object tracking, data association and object pose estimation) to which, in turn, the evidential formalism is able to provide interesting new solutions. Finally, some initial steps towards a generalization of the notion of total probability to belief functions are taken, in the perspective of endowing the theory of evidence with a complete battery of estimation and inference tools to the benefit of all scientists and practitioners.

cs.CV↗

arXiv2018

Predicting Action Tubes

In this work, we present a method to predict an entire `action tube' (a set of temporally linked bounding boxes) in a trimmed video just by observing a smaller subset of it. Predicting where an action is going to take place in the near future is essential to many computer vision based applications such as autonomous driving or surgical robotics. Importantly, it has to be done in real-time and in an online fashion. We propose a Tube Prediction network (TPnet) which jointly predicts the past, present and future bounding boxes along with their action classification scores. At test time TPnet is used in a (temporal) sliding window setting, and its predictions are put into a tube estimation framework to construct/predict the video long action tubes not only for the observed part of the video but also for the unobserved part. Additionally, the proposed action tube predictor helps in completing action tubes for unobserved segments of the video. We quantitatively demonstrate the latter ability, and the fact that TPnet improves state-of-the-art detection performance, on one of the standard action detection benchmarks - J-HMDB-21 dataset.

cs.CV↗

arXiv2018

Belief likelihood function for generalised logistic regression

The notion of belief likelihood function of repeated trials is introduced, whenever the uncertainty for individual trials is encoded by a belief measure (a finite random set). This generalises the traditional likelihood function, and provides a natural setting for belief inference from statistical data. Factorisation results are proven for the case in which conjunctive or disjunctive combination are employed, leading to analytical expressions for the lower and upper likelihoods of `sharp' samples in the case of Bernoulli trials, and to the formulation of a generalised logistic regression framework.

math.ST↗

arXiv2018

TraMNet - Transition Matrix Network for Efficient Action Tube Proposals

Current state-of-the-art methods solve spatiotemporal action localisation by extending 2D anchors to 3D-cuboid proposals on stacks of frames, to generate sets of temporally connected bounding boxes called \textit{action micro-tubes}. However, they fail to consider that the underlying anchor proposal hypotheses should also move (transition) from frame to frame, as the actor or the camera does. Assuming we evaluate $n$ 2D anchors in each frame, then the number of possible transitions from each 2D anchor to the next, for a sequence of $f$ consecutive frames, is in the order of $O(n^f)$, expensive even for small values of $f$. To avoid this problem, we introduce a Transition-Matrix-based Network (TraMNet) which relies on computing transition probabilities between anchor proposals while maximising their overlap with ground truth bounding boxes across frames, and enforcing sparsity via a transition threshold. As the resulting transition matrix is sparse and stochastic, this reduces the proposal hypothesis search space from $O(n^f)$ to the cardinality of the thresholded matrix. At training time, transitions are specific to cell locations of the feature maps, so that a sparse (efficient) transition matrix is used to train the network. At test time, a denser transition matrix can be obtained either by decreasing the threshold or by adding to it all the relative transitions originating from any cell location, allowing the network to handle transitions in the test data that might not have been present in the training data, and making detection translation-invariant. Finally, we show that our network can handle sparse annotations such as those available in the DALY dataset. We report extensive experiments on the DALY, UCF101-24 and Transformed-UCF101-24 datasets to support our claims.

eess.IV↗

arXiv2018

Action Detection from a Robot-Car Perspective

We present the new Road Event and Activity Detection (READ) dataset, designed and created from an autonomous vehicle perspective to take action detection challenges to autonomous driving. READ will give scholars in computer vision, smart cars and machine learning at large the opportunity to conduct research into exciting new problems such as understanding complex (road) activities, discerning the behaviour of sentient agents, and predicting both the label and the location of future actions and events, with the final goal of supporting autonomous decision making.

cs.CV↗

arXiv2018

Incremental Tube Construction for Human Action Detection

Current state-of-the-art action detection systems are tailored for offline batch-processing applications. However, for online applications like human-robot interaction, current systems fall short, either because they only detect one action per video, or because they assume that the entire video is available ahead of time. In this work, we introduce a real-time and online joint-labelling and association algorithm for action detection that can incrementally construct space-time action tubes on the most challenging action videos in which different action categories occur concurrently. In contrast to previous methods, we solve the detection-window association and action labelling problems jointly in a single pass. We demonstrate superior online association accuracy and speed (2.2ms per frame) as compared to the current state-of-the-art offline systems. We further demonstrate that the entire action detection pipeline can easily be made to work effectively in real-time using our action tube construction algorithm.

cs.CV↗

arXiv2017

Online Real-time Multiple Spatiotemporal Action Localisation and Prediction

We present a deep-learning framework for real-time multiple spatio-temporal (S/T) action localisation, classification and early prediction. Current state-of-the-art approaches work offline and are too slow to be useful in real- world settings. To overcome their limitations we introduce two major developments. Firstly, we adopt real-time SSD (Single Shot MultiBox Detector) convolutional neural networks to regress and classify detection boxes in each video frame potentially containing an action of interest. Secondly, we design an original and efficient online algorithm to incrementally construct and label `action tubes' from the SSD frame level detections. As a result, our system is not only capable of performing S/T detection in real time, but can also perform early action prediction in an online fashion. We achieve new state-of-the-art results in both S/T action localisation and early action prediction on the challenging UCF101-24 and J-HMDB-21 benchmarks, even when compared to the top offline competitors. To the best of our knowledge, ours is the first real-time (up to 40fps) system able to perform online S/T action localisation and early action prediction on the untrimmed videos of UCF101-24.

cs.CV↗

arXiv2017

AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture

Dominant approaches to action detection can only provide sub-optimal solutions to the problem, as they rely on seeking frame-level detections, to later compose them into "action tubes" in a post-processing step. With this paper we radically depart from current practice, and take a first step towards the design and implementation of a deep network architecture able to classify and regress whole video subsets, so providing a truly optimal solution of the action detection problem. In this work, in particular, we propose a novel deep net framework able to regress and classify 3D region proposals spanning two successive video frames, whose core is an evolution of classical region proposal networks (RPNs). As such, our 3D-RPN net is able to effectively encode the temporal aspect of actions by purely exploiting appearance, as opposed to methods which heavily rely on expensive flow maps. The proposed model is end-to-end trainable and can be jointly optimised for action localisation and classification in a single step. At test time the network predicts "micro-tubes" encompassing two successive frames, which are linked up into complete action tubes via a new algorithm which exploits the temporal encoding learned by the network and cuts computation time by 50%. Promising results on the J-HMDB-21 and UCF-101 action detection datasets show that our model does outperform the state-of-the-art when relying purely on appearance.

cs.CV↗

arXiv2017

Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos

Current state-of-the-art human action recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame. In this work we address the problem of action localisation and instance segmentation in which multiple concurrent actions of the same class may be segmented out of an image sequence. We cast the action tube extraction as an energy maximisation problem in which configurations of region proposals in each frame are assigned a cost and the best action tubes are selected via two passes of dynamic programming. One pass associates region proposals in space and time for each action category, and another pass is used to solve for the tube's temporal extent and to enforce a smooth label sequence through the video. In addition, by taking advantage of recent work on action foreground-background segmentation, we are able to associate each tube with class-specific segmentations. We demonstrate the performance of our algorithm on the challenging LIRIS-HARL dataset and achieve a new state-of-the-art result which is 14.3 times better than previous methods.

cs.CV↗

arXiv2016

Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos

In this work, we propose an approach to the spatiotemporal localisation (detection) and classification of multiple concurrent actions within temporally untrimmed videos. Our framework is composed of three stages. In stage 1, appearance and motion detection networks are employed to localise and score actions from colour images and optical flow. In stage 2, the appearance network detections are boosted by combining them with the motion detection scores, in proportion to their respective spatial overlap. In stage 3, sequences of detection boxes most likely to be associated with a single action instance, called action tubes, are constructed by solving two energy maximisation problems via dynamic programming. While in the first pass, action paths spanning the whole video are built by linking detection boxes over time using their class-specific scores and their spatial overlap, in the second pass, temporal trimming is performed by ensuring label consistency for all constituting detection boxes. We demonstrate the performance of our algorithm on the challenging UCF101, J-HMDB-21 and LIRIS-HARL datasets, achieving new state-of-the-art results across the board and significantly increasing detection speed at test time. We achieve a huge leap forward in action detection performance and report a 20% and 11% gain in mAP (mean average precision) on UCF-101 and J-HMDB-21 datasets respectively when compared to the state-of-the-art.

cs.CV↗

arXiv2016

Untrimmed Video Classification for Activity Detection: submission to ActivityNet Challenge

Current state-of-the-art human activity recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame. We propose a simple, yet effective, method for the temporal detection of activities in temporally untrimmed videos with the help of untrimmed classification. Firstly, our model predicts the top k labels for each untrimmed video by analysing global video-level features. Secondly, frame-level binary classification is combined with dynamic programming to generate the temporally trimmed activity proposals. Finally, each proposal is assigned a label based on the global label, and scored with the score of the temporal activity proposal and the global score. Ultimately, we show that untrimmed video classification models can be used as stepping stone for temporal detection.

cs.CV↗

arXiv2016

Active Learning for Online Recognition of Human Activities from Streaming Videos

Recognising human activities from streaming videos poses unique challenges to learning algorithms: predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily long. Furthermore, as parameter tuning is problematic in a streaming setting, suitable approaches should be parameterless, and make no assumptions on what class labels may occur in the stream. We present here an approach to the recognition of human actions from streaming data which meets all these requirements by: (1) incrementally learning a model which adaptively covers the feature space with simple local classifiers; (2) employing an active learning strategy to reduce annotation requests; (3) achieving promising accuracy within a fixed model size. Extensive experiments on standard benchmarks show that our approach is competitive with state-of-the-art non-incremental methods, and outperforms the existing active incremental baselines.

stat.ML↗

arXiv2014

Consistent transformations of belief functions

Consistent belief functions represent collections of coherent or non-contradictory pieces of evidence, but most of all they are the counterparts of consistent knowledge bases in belief calculus. The use of consistent transformations cs[.] in a reasoning process to guarantee coherence can therefore be desirable, and generalizes similar techniques in classical logic. Transformations can be obtained by minimizing an appropriate distance measure between the original belief function and the collection of consistent ones. We focus here on the case in which distances are measured using classical Lp norms, in both the "mass space" and the "belief space" representation of belief functions. While mass consistent approximations reassign the mass not focussed on a chosen element of the frame either to the whole frame or to all supersets of the element on an equal basis, approximations in the belief space do distinguish these focal elements according to the "focussed consistent transformation" principle. The different approximations are interpreted and compared, with the help of examples.

cs.AI↗

arXiv2014

Feature sampling and partitioning for visual vocabulary generation on large action classification datasets

The recent trend in action recognition is towards larger datasets, an increasing number of action classes and larger visual vocabularies. State-of-the-art human action classification in challenging video data is currently based on a bag-of-visual-words pipeline in which space-time features are aggregated globally to form a histogram. The strategies chosen to sample features and construct a visual vocabulary are critical to performance, in fact often dominating performance. In this work we provide a critical evaluation of various approaches to building a vocabulary and show that good practises do have a significant impact. By subsampling and partitioning features strategically, we are able to achieve state-of-the-art results on 5 major action recognition datasets using relatively small visual vocabularies.

cs.CV↗

arXiv2014

Robust Temporally Coherent Laplacian Protrusion Segmentation of 3D Articulated Bodies

In motion analysis and understanding it is important to be able to fit a suitable model or structure to the temporal series of observed data, in order to describe motion patterns in a compact way, and to discriminate between them. In an unsupervised context, i.e., no prior model of the moving object(s) is available, such a structure has to be learned from the data in a bottom-up fashion. In recent times, volumetric approaches in which the motion is captured from a number of cameras and a voxel-set representation of the body is built from the camera views, have gained ground due to attractive features such as inherent view-invariance and robustness to occlusions. Automatic, unsupervised segmentation of moving bodies along entire sequences, in a temporally-coherent and robust way, has the potential to provide a means of constructing a bottom-up model of the moving body, and track motion cues that may be later exploited for motion classification. Spectral methods such as locally linear embedding (LLE) can be useful in this context, as they preserve "protrusions", i.e., high-curvature regions of the 3D volume, of articulated shapes, while improving their separation in a lower dimensional space, making them in this way easier to cluster. In this paper we therefore propose a spectral approach to unsupervised and temporally-coherent body-protrusion segmentation along time sequences. Volumetric shapes are clustered in an embedding space, clusters are propagated in time to ensure coherence, and merged or split to accommodate changes in the body's topology. Experiments on both synthetic and real sequences of dense voxel-set data are shown. This supports the ability of the proposed method to cluster body-parts consistently over time in a totally unsupervised fashion, its robustness to sampling density and shape quality, and its potential for bottom-up model construction

cs.CV↗