We derive analytic bounds on the noise invariance of majority vote classifiers operating on compressed inputs. Specifically, starting from recent bounds on the true risk of majority vote classifiers, we extend the applicability of PAC-Bayesian theory to quantify the resilience of majority votes to input noise stemming from compression. The derived bounds are intuitive in binary classification settings, where they can be measured as expressions of voter differentials and voter pair agreement. By combining measures of input distortion with analytic guarantees on noise invariance, we prescribe rate-efficient machines to compress inputs without affecting subsequent classification. Our validation shows how bounding noise invariance can inform the compression stage for any majority vote classifier such that worst-case implications of bad input reconstructions are known, and inputs can be compressed to the minimum amount of information needed prior to inference.

The proliferation of low-cost DRAM chipsets now begins to allow for the consideration of substantially-increased decoded picture buffers in advanced video coding standards such as HEVC, VVC, and Google VP9. At the same time, the increasing demand for rapid scene changes and multiple scene repetitions in entertainment or broadcast content indicates that extending the frame referencing interval to tens of minutes or even the entire video sequence may offer coding gains, as long as one is able to identify frame similarity in a computationally- and memory-efficient manner. Motivated by these observations, we propose a “stitching” method that defines a reference buffer and a reference frame selection algorithm. Our proposal extends the referencing interval of inter-frame video coding to the entire length of video sequences. Our reference frame selection algorithm uses well-established feature descriptor methods that describe frame structural elements in a compact and semantically-rich manner. We propose to combine such compact descriptors with a similarity scoring mechanism in order to select the frames to be “stitched” to reference picture buffers of advanced inter-frame encoders like HEVC, VVC, and VP9 without breaking standard compliance. Our evaluation on synthetic and real-world video sequences with the HEVC and VVC reference encoders shows that our method offers significant rate gains, with complexity and memory requirements that remain manageable for practical encoders and decoders.

We propose a novel database management framework for data delivery services based on Store-Carry-Forward (SCF) techniques. The platform we present consists of heterogeneous wireless opportunistic networks of long-range narrowband and short-range broadband communications. We introduce a blockchain-based method by which to verify the record of delivery events on a decentralized network. A new consensus mechanism named proof-of-forwarding (PoF) is proposed to substitute the function of previously proposed proof-of-work (PoW) methods, while significantly improving computational complexities of block generation. Specifically, in our proposal a block is generated exclusively when data delivery agents perform node-to-node direct communication using a short-range high-speed wireless standard to deliver data. We additionally propose a digital signature overlay to prevent malicious nodes from producing fake transactions without any effort to carry data content to recipients. Simulation results show that our blockchain-based framework robustly manages data delivery records, where 97% of Distributed Denial-of-Service (DDoS) attacks can be prevented even when half of the entire nodes are assumed to be malicious.

Advanced video classification systems decode video frames to derive texture and motion representations for ingestion and analysis by spatio-temporal deep convolutional neural networks (CNNs). However, when considering visual Internet-of-Things applications, surveillance systems, and semantic crawlers of large video repositories, the video capture and the CNN-based semantic analysis parts do not tend to be co-located. This necessitates the transport of compressed video over networks and incurs significant overhead in bandwidth and energy consumption, thereby significantly undermining the deployment potential of such systems. In this paper, we investigate the trade-off between the encoding bitrate and the achievable accuracy of CNN-based video classification models that directly ingest AVC/H.264 and HEVC encoded videos. Instead of retaining entire compressed video bitstreams and applying complex optical flow calculations prior to CNN processing, we only retain motion vector and select texture information at significantly reduced bitrates and apply no additional processing prior to CNN ingestion. Based on three CNN architectures and two action recognition datasets, we achieve 11%-94% savings in bitrate with marginal effect on classification accuracy. A model-based selection between multiple CNNs increases these savings further to the point where, if up to 7% loss of accuracy can be tolerated, video classification can take place with as little as 3 kb/s for the transport of the required compressed video information to the system implementing the CNN models.

We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate results can vary for different input space partitions. Therefore, we consider mixtures where experts require different amounts of data, and train a sparse gating function to divide the input space for each expert. By appropriate hyperparameter selection, our approach is able to bias mixtures of experts towards selecting specific experts over others. In this way, we show that the data transfer optimization between visual sensing and processing can be solved as a convex optimization problem. To demonstrate the relation between data availability and performance, we evaluate biased mixtures on a range of mainstream computer vision problems, namely: (i) single shot detection, (ii) image super resolution, and (iii) realtime video action classification. For all cases, and when experts constitute modified baselines to meet different limits on allowed data utility, biased mixtures significantly outperform previous work optimized to meet the same constraints on available data.

Neuromorphic vision sensing (NVS) devices represent visual information as sequences of asynchronous discrete events (a.k.a., "spikes") in response to changes in scene reflectance. Unlike conventional active pixel sensing (APS), NVS allows for significantly higher event sampling rates at substantially increased energy efficiency and robustness to illumination changes. However, feature representation for NVS is far behind its APS-based counterparts, resulting in lower performance in high-level computer vision tasks. To fully utilize its sparse and asynchronous nature, we propose a compact graph representation for NVS, which allows for end-to-end learning with graph convolution neural networks. We couple this with a novel end-to-end feature learning framework that accommodates both appearancebased and motion-based tasks. The core of our framework comprises a spatial feature learning module, which utilizes residual-graph convolutional neural networks (RG-CNN), for end-to-end learning of appearance-based features directly from graphs. We extend this with our proposed Graph2Grid block and temporal feature learning module for efficiently modelling temporal dependencies over multiple graphs and a long temporal extent. We show how our framework can be configured for object classification, action recognition and action similarity labeling. Importantly, our approach preserves the spatial and temporal coherence of spike events, while requiring less computation and memory. The experimental validation shows that our proposed framework outperforms all recent methods on standard datasets. Finally, to address the absence of large real-world NVS datasets for complex recognition tasks, we introduce, evaluate and make available the American Sign Language letters (ASL-DVS), as well as human action dataset (UCF101-DVS, HMDB51-DVS and ASLAN-DVS).

Neuromorphic vision sensing (NVS) hardware is now gaining traction as a low-power/high-speed visual sensing technology that circumvents the limitations of conventional active pixel sensing (APS) cameras. While object detection and tracking models have been investigated in conjunction with NVS, there is currently little work on NVS for higher-level semantic tasks, such as action recognition. Contrary to recent work that considers homogeneous transfer between flow domains (optical flow to motion vectors), we propose to embed an NVS emulator into a multi-modal transfer learning framework that carries out heterogeneous transfer from optical flow to NVS. The potential of our framework is showcased by the fact that, for the first time, our NVS-based results achieve comparable action recognition performance to motion-vector or optical-flow based methods (i.e., accuracy on UCF-101 within 8.8% of I3D with optical flow), with the NVS emulator and NVS camera hardware offering 3 to 6 orders of magnitude faster frame generation (respectively) compared to standard Brox optical flow. Beyond this significant advantage, our CNN processing is found to have the lowest total GFLOP count against all competing methods (up to 7.7 times complexity saving compared to I3D with optical flow).

Neuromorphic vision sensing (NVS) devices represent visual information as sequences of asynchronous discrete events (a.k.a., "spikes'") in response to changes in scene reflectance. Unlike conventional active pixel sensing (APS), NVS allows for significantly higher event sampling rates at substantially increased energy efficiency and robustness to illumination changes. However, object classification with NVS streams cannot leverage on state-of-the-art convolutional neural networks (CNNs), since NVS does not produce frame representations. To circumvent this mismatch between sensing and processing with CNNs, we propose a compact graph representation for NVS. We couple this with novel residual graph CNN architectures and show that, when trained on spatio-temporal NVS data for object classification, such residual graph CNNs preserve the spatial and temporal coherence of spike events, while requiring less computation and memory. Finally, to address the absence of large real-world NVS datasets for complex recognition tasks, we present and make available a 100k dataset of NVS recordings of the American sign language letters, acquired with an iniLabs DAVIS240c device under real-world conditions.

We investigate video classification via a two-stream convolutional neural network (CNN) design that directly ingests information extracted from compressed video bitstreams. Our approach begins with the observation that all modern video codecs divide the input frames into macroblocks (MBs). We demonstrate that selective access to MB motion vector (MV) information within compressed video bitstreams can also provide for selective, motion-adaptive, MB pixel decoding (a.k.a., MB texture decoding). This in turn allows for the derivation of spatio-temporal video activity regions at extremely high speed in comparison to conventional full-frame decoding followed by optical flow estimation. In order to evaluate the accuracy of a video classification framework based on such activity data, we independently train two CNN architectures on MB texture and MV correspondences and then fuse their scores to derive the final classification of each test video. Evaluation on two standard data sets shows that the proposed approach is competitive with the best two-stream video classification approaches found in the literature. At the same time: 1) a CPU-based realization of our MV extraction is over 977 times faster than GPU-based optical flow methods; 2) selective decoding is up to 12 times faster than full-frame decoding; and 3) our proposed spatial and temporal CNNs perform inference at 5 to 49 times lower cloud computing cost than the fastest methods from the literature.

Advanced video classification systems decode video frames to derive the necessary texture and motion representations for ingestion and analysis by spatio-temporal deep convolutional neural networks (CNNs). However, when considering visual Internet -of- Things applications, surveillance systems and semantic crawlers of large video repositories, the compressed video content and the CNN-based semantic analysis parts do not tend to be co-located. This necessitates the transport of compressed video over networks and incurs significant overhead in bandwidth and energy consumption, thereby significantly undermining the deployment potential of such systems. In this paper, we investigate the trade-off between the encoding bitrate and the achievable accuracy of CNN-based video classification that ingests AVC/H.264 encoded videos. Instead of entire compressed video bitstreams, we only retain motion vector and selected texture information at significantly reduced bitrates. Based on two CNN architectures and two action recognition datasets, we achieve 38%-59% saving in bitrate with marginal impact in classification accuracy. A simple rate-based selection between the two CNNs shows that even further bitrate savings are possible with graceful degradation in accuracy. This may allow for rate/accuracy-optimized CNN-based video classification over networks.

We investigate video classification via a 3D deep convolutional neural network (CNN) that directly ingests compressed bitstream information. This idea is based on the observation that video macroblock (MB) motion vectors (that are very compact and directly available from the compressed bitstream) are inherently capturing local spatio-temporal changes in each video scene. Our results on two standard video datasets show that our approach outperforms pixel-based approaches and remains within 7 percentile points from the best classification results reported by highly-complex optical-flow & deep-CNN methods. At the same time, a CPU-based realization of our approach is found to be more than 2500 times faster in the motion extraction in comparison to GPU-based optical flow methods and also offers 2 to 3.4-fold reduction in the utilized deep CNN weights compared to recent architectures. This indicates that deep learning based on compressed video bitstream information may allow for advanced video classification to be deployed in very large datasets using commodity CPU hardware. Source code is available at http://www.github.com/mvcnn.

We propose a novel vector aggregation technique for compact video representation, with application in accurate similarity detection within large video datasets. The current state-of-the-art in visual search is formed by the vector of locally aggregated descriptors (VLAD) of Jegou et al. VLAD generates compact video representations based on scale-invariant feature transform (SIFT) vectors (extracted per frame) and local feature centers computed over a training set. With the aim to increase robustness to visual distortions, we propose a new approach that operates at a coarser level in the feature representation. We create vectors of locally aggregated centers (VLAC) by first clustering SIFT features to obtain local feature centers (LFCs) and then encoding the latter with respect to given centers of local feature centers (CLFCs), extracted from a training set. The sum-of-differences between the LFCs and the CLFCs are aggregated to generate an extremely-compact video description used for accurate video segment similarity detection. Experimentation using a video dataset, comprising more than 1000 minutes of content from the Open Video Project, shows that VLAC obtains substantial gains in terms of mean Average Precision (mAP) against VLAD and the hyper-pooling method of Douze et al., under the same compaction factor and the same set of distortions.