Search for: All records

Video anomaly detection (VAD) – commonly formulated as a multiple-instance learning problem in a weakly-supervised manner due to its labor-intensive nature – is a challenging problem in video surveillance where the frames of anomaly need to be localized in an untrimmed video. In this paper, we first propose to utilize the ViT-encoded visual features from CLIP, in contrast with the conventional C3D or I3D features in the domain, to efficiently extract discriminative representations in the novel technique. We then model temporal de- pendencies and nominate the snippets of interest by leveraging our proposed Temporal Self-Attention (TSA). The ablation study confirms the effectiveness of TSA and ViT feature. The extensive experiments show that our proposed CLIP-TSA outperforms the existing state-of-the-art (SOTA) methods by a large margin on three commonly-used benchmark datasets in the VAD problem (UCF-Crime, ShanghaiTech Campus and XD-Violence). Our source code is available at https:// github.com/joos2010kj/CLIP-TSA. 

Video Paragraph Captioning aims to generate a multi-sentence description of an untrimmed video with multiple temporal event locations in a coherent storytelling. Following the human perception process, where the scene is effectively understood by decomposing it into visual (e.g. human, animal) and non-visual components (e.g. action, relations) under the mutual influence of vision and language, we first propose a visual-linguistic (VL) feature. In the proposed VL feature, the scene is modeled by three modalities including (i) a global visual environment; (ii) local visual main agents; (iii) linguistic scene elements. We then introduce an autoregressive Transformer-in-Transformer (TinT) to simultaneously capture the semantic coherence of intra- and inter-event contents within a video. Finally, we present a new VL contrastive loss function to guarantee the learnt embedding features are consistent with the captions semantics. Comprehensive experiments and extensive ablation studies on the ActivityNet Captions and YouCookII datasets show that the proposed Visual-Linguistic Transformer-in-Transform (VLTinT) outperforms previous state-of-the-art methods in terms of accuracy and diversity. The source code is made publicly available at: https://github.com/UARK-AICV/VLTinT. 

In this paper, we present a novel Deformable Neural Articulations Network (DNA-Net), which is a template- free learning-based method for dynamic 3D human reconstruction from a single RGB-D sequence. Our proposed DNA-Net includes a Neural Articulation Prediction Net- work (NAP-Net), which is capable of representing non-rigid motions of a human by learning to predict a set of articulated bones to follow movements of the human in the in- put sequence. Moreover, DNA-Net also include Signed Distance Field Network (SDF-Net) and Appearance Network (Color-Net), which take advantage of the powerful neural implicit functions in modeling 3D geometries and appear- ance. Finally, to avoid the reliance on external optical flow estimators to obtain deformation cues like previous related works, we propose a novel training loss, namely Easy-to- Hard Geometric-based, which is a simple strategy that inherits the merits of Chamfer distance to achieve good de- formation guidance while still avoiding its limitation of lo- cal mismatches sensitivity. DNA-Net is trained end-to-end in a self-supervised manner directly on the input sequence to obtain 3D reconstructions of the input objects. Quantitative results on videos of DeepDeform dataset show that DNA-Net outperforms related state-of-the-art methods with an adequate gaps, qualitative results additionally prove that our method can reconstruct human shapes with high fidelity and details. 

The past decade has witnessed the great success of deep neural networks in various domains. However, deep neural networks are very resource-intensive in terms of energy consumption, data requirements, and high computational costs. With the recent increasing need for the autonomy of machines in the real world, e.g., self-driving vehicles, drones, and collaborative robots, exploitation of deep neural networks in those applications has been actively investigated. In those applications, energy and computational efficiencies are especially important because of the need for real-time responses and the limited energy supply. A promising solution to these previously infeasible applications has recently been given by biologically plausible spiking neural networks. Spiking neural networks aim to bridge the gap between neuroscience and machine learning, using biologically realistic models of neurons to carry out the computation. Due to their functional similarity to the biological neural network, spiking neural networks can embrace the sparsity found in biology and are highly compatible with temporal code. Our contributions in this work are: (i) we give a comprehensive review of theories of biological neurons; (ii) we present various existing spike-based neuron models, which have been studied in neuroscience; (iii) we detail synapse models; (iv) we provide a review of artificial neural networks; (v) we provide detailed guidance on how to train spike-based neuron models; (vi) we revise available spike-based neuron frameworks that have been developed to support implementing spiking neural networks; (vii) finally, we cover existing spiking neural network applications in computer vision and robotics domains. The paper concludes with discussions of future perspectives.

 

Medical image segmentation is one of the most challenging tasks in medical image analysis and widely developed for many clinical applications. While deep learning-based approaches have achieved impressive performance in semantic segmentation, they are limited to pixel-wise settings with imbalanced-class data problems and weak boundary object segmentation in medical images. In this paper, we tackle those limitations by developing a new two-branch deep network architecture which takes both higher level features and lower level features into account. The first branch extracts higher level feature as region information by a common encoder-decoder network structure such as Unet and FCN, whereas the second branch focuses on lower level features as support information around the boundary and processes in parallel to the first branch. Our key contribution is the second branch named Narrow Band Active Contour (NB-AC) attention model which treats the object contour as a hyperplane and all data inside a narrow band as support information that influences the position and orientation of the hyperplane. Our proposed NB-AC attention model incorporates the contour length with the region energy involving a fixed-width band around the curve or surface. The proposed network loss contains two fitting terms: (i) a high level feature (i.e., region) fitting term from the first branch; (ii) a lower level feature (i.e., contour) fitting term from the second branch including the (ii1) length of the object contour and (ii2) regional energy functional formed by the homogeneity criterion of both the inner band and outer band neighboring the evolving curve or surface. The proposed NB-AC loss can be incorporated into both 2D and 3D deep network architectures. The proposed network has been evaluated on different challenging medical image datasets, including DRIVE, iSeg17, MRBrainS18 and Brats18. The experimental results have shown that the proposed NB-AC loss outperforms other mainstream loss functions: Cross Entropy, Dice, Focal on two common segmentation frameworks Unet and FCN. Our 3D network which is built upon the proposed NB-AC loss and 3DUnet framework achieved state-of-the-art results on multiple volumetric datasets. 

In recent years, deep neural networks have achieved state-of-the-art performance in a variety of recognition and segmentation tasks in medical imaging including brain tumor segmentation. We investigate that segmenting a brain tumor is facing to the imbalanced data problem where the number of pixels belonging to the background class (non tumor pixel) is much larger than the number of pixels belonging to the foreground class (tumor pixel). To address this problem, we propose a multitask network which is formed as a cascaded structure. Our model consists of two targets, i.e., (i) effectively differentiate the brain tumor regions and (ii) estimate the brain tumor mask. The first objective is performed by our proposed contextual brain tumor detection network, which plays a role of an attention gate and focuses on the region around brain tumor only while ignoring the far neighbor background which is less correlated to the tumor. Different from other existing object detection networks which process every pixel, our contextual brain tumor detection network only processes contextual regions around ground-truth instances and this strategy aims at producing meaningful regions proposals. The second objective is built upon a 3D atrous residual network and under an encode-decode network in order to effectively segment both large and small objects (brain tumor). Our 3D atrous residual network is designed with a skip connection to enables the gradient from the deep layers to be directly propagated to shallow layers, thus, features of different depths are preserved and used for refining each other. In order to incorporate larger contextual information from volume MRI data, our network utilizes the 3D atrous convolution with various kernel sizes, which enlarges the receptive field of filters. Our proposed network has been evaluated on various datasets including BRATS2015, BRATS2017 and BRATS2018 datasets with both validation set and testing set. Our performance has been benchmarked by both regionbased metrics and surface-based metrics. We also have conducted comparisons against state-of-the-art approaches