Learning Long-term Structural Dependencies for Video Salient Object Detection

Learning Complementary Spatial-Temporal Transformer for Video Salient Object Detection

Besides combining appearance and motion information, another crucial factor for video salient object detection (VSOD) is to mine spatial-temporal (ST) knowledge, including complementary long-short temporal cues and global-local spatial context from neighboring frames. However, the existing methods only explored part of them and ignored their complementarity. In this article, we propose a novel complementary ST transformer (CoSTFormer) for VSOD, which has a short-global branch and a long-local branch to aggregate complementary ST contexts. The former integrates the global context from the neighboring two frames using dense pairwise attention, while the latter is designed to fuse long-term temporal information from more consecutive frames with local attention windows. In this way, we decompose the ST context into a short-global part and a long-local part and leverage the powerful transformer to model the context relationship and learn their complementarity. To solve the contradiction between local window attention and object motion, we propose a novel flow-guided window attention (FGWA) mechanism to align the attention windows with object and camera movements. Furthermore, we deploy CoSTFormer on fused appearance and motion features, thus enabling the effective combination of all three VSOD factors. Besides, we present a pseudo video generation method to synthesize sufficient video clips from static images for training ST saliency models. Extensive experiments have verified the effectiveness of our method and illustrated that we achieve new state-of-the-art results on several benchmark datasets.

Interactive spatio-temporal feature learning network for video foreground detection

Video foreground detection (VFD), as one of the basic pre-processing tasks, is very essential for subsequent target tracking and recognition. However, due to the interference of shadow, dynamic background, and camera jitter, constructing a suitable detection network is still challenging. Recently, convolution neural networks have proved its reliability in many fields with their powerful feature extraction ability. Therefore, an interactive spatio-temporal feature learning network (ISFLN) for VFD is proposed in this paper. First, we obtain the deep and shallow spatio-temporal information of two paths with multi-level and multi-scale. The deep feature is conducive to enhancing feature identification capabilities, while the shallow feature is dedicated to fine boundary segmentation. Specifically, an interactive multi-scale feature extraction module (IMFEM) is designed to facilitate the information transmission between different types of features. Then, a multi-level feature enhancement module (MFEM), which provides precise object knowledge for decoder, is proposed to guide the coding information of each layer by the fusion spatio-temporal difference characteristic. Experimental results on LASIESTA, CDnet2014, INO, and AICD datasets demonstrate that the proposed ISFLN is more effective than the existing advanced methods.

Sentiment Analysis in Twitter Based on Knowledge Graph and Deep Learning Classification

The traditional way to address the problem of sentiment classification is based on machine learning techniques; however, these models are not able to grasp all the richness of the text that comes from different social media, personal web pages, blogs, etc., ignoring the semantic of the text. Knowledge graphs give a way to extract structured knowledge from images and texts in order to facilitate their semantic analysis. This work proposes a new hybrid approach for Sentiment Analysis based on Knowledge Graphs and Deep Learning techniques to identify the sentiment polarity (positive or negative) in short documents, such as posts on Twitter. In this proposal, tweets are represented as graphs; then, graph similarity metrics and a Deep Learning classification algorithm are applied to produce sentiment predictions. This approach facilitates the traceability and interpretability of the classification results, thanks to the integration of the Local Interpretable Model-agnostic Explanations (LIME) model at the end of the pipeline. LIME allows raising trust in predictive models, since the model is not a black box anymore. Uncovering the black box allows understanding and interpreting how the network could distinguish between sentiment polarities. Each phase of the proposed approach conformed by pre-processing, graph construction, dimensionality reduction, graph similarity, sentiment prediction, and interpretability steps is described. The proposal is compared with character n-gram embeddings-based Deep Learning models to perform Sentiment Analysis. Results show that the proposal is able to outperforms classical n-gram models, with a recall up to 89% and F1-score of 88%.

Multi-Modal Interaction Graph Convolutional Network for Temporal Language Localization in Videos

This paper focuses on tackling the problem of temporal language localization in videos, which aims to identify the start and end points of a moment described by a natural language sentence in an untrimmed video. However, it is non-trivial since it requires not only the comprehensive understanding of the video and sentence query, but also the accurate semantic correspondence capture between them. Existing efforts are mainly centered on exploring the sequential relation among video clips and query words to reason the video and sentence query, neglecting the other intra-modal relations (e.g., semantic similarity among video clips and syntactic dependency among the query words). Towards this end, in this work, we propose a Multi-modal Interaction Graph Convolutional Network (MIGCN), which jointly explores the complex intra-modal relations and inter-modal interactions residing in the video and sentence query to facilitate the understanding and semantic correspondence capture of the video and sentence query. In addition, we devise an adaptive context-aware localization method, where the context information is taken into the candidate moments and the multi-scale fully connected layers are designed to rank and adjust the boundary of the generated coarse candidate moments with different lengths. Extensive experiments on Charades-STA and ActivityNet datasets demonstrate the promising performance and superior efficiency of our model.

An Unified Recurrent Video Object Segmentation Framework for Various Surveillance Environments

Moving object segmentation (MOS) in videos received considerable attention because of its broad security-based applications like robotics, outdoor video surveillance, self-driving cars, etc. The current prevailing algorithms highly depend on additional trained modules for other applications or complicated training procedures or neglect the inter-frame spatio-temporal structural dependencies. To address these issues, a simple, robust, and effective unified recurrent edge aggregation approach is proposed for MOS, in which additional trained modules or fine-tuning on a test video frame(s) are not required. Here, a recurrent edge aggregation module (REAM) is proposed to extract effective foreground relevant features capturing spatio-temporal structural dependencies with encoder and respective decoder features connected recurrently from previous frame. These REAM features are then connected to a decoder through skip connections for comprehensive learning named as temporal information propagation. Further, the motion refinement block with multi-scale dense residual is proposed to combine the features from the optical flow encoder stream and the last REAM module for holistic feature learning. Finally, these holistic features and REAM features are given to the decoder block for segmentation. To guide the decoder block, previous frame output with respective scales is utilized. The different configurations of training-testing techniques are examined to evaluate the performance of the proposed method. Specifically, outdoor videos often suffer from constrained visibility due to different environmental conditions and other small particles in the air that scatter the light in the atmosphere. Thus, comprehensive result analysis is conducted on six benchmark video datasets with different surveillance environments. We demonstrate that the proposed method outperforms the state-of-the-art methods for MOS without any pre-trained module, fine-tuning on the test video frame(s) or complicated training.

Exploring Rich and Efficient Spatial Temporal Interactions for Real-Time Video Salient Object Detection

We have witnessed a growing interest in video salient object detection (VSOD) techniques in today's computer vision applications. In contrast with temporal information (which is still considered a rather unstable source thus far), the spatial information is more stable and ubiquitous, thus it could influence our vision system more. As a result, the current main-stream VSOD approaches have inferred and obtained their saliency primarily from the spatial perspective, still treating temporal information as subordinate. Although the aforementioned methodology of focusing on the spatial aspect is effective in achieving a numeric performance gain, it still has two critical limitations. First, to ensure the dominance by the spatial information, its temporal counterpart remains inadequately used, though in some complex video scenes, the temporal information may represent the only reliable data source, which is critical to derive the correct VSOD. Second, both spatial and temporal saliency cues are often computed independently in advance and then integrated later on, while the interactions between them are omitted completely, resulting in saliency cues with limited quality. To combat these challenges, this paper advocates a novel spatiotemporal network, where the key innovation is the design of its temporal unit. Compared with other existing competitors (e.g., convLSTM), the proposed temporal unit exhibits an extremely lightweight design that does not degrade its strong ability to sense temporal information. Furthermore, it fully enables the computation of temporal saliency cues that interact with their spatial counterparts, ultimately boosting the overall VSOD performance and realizing its full potential towards mutual performance improvement for each. The proposed method is easy to implement yet still effective, achieving high-quality VSOD at 50 FPS in real-time applications.