With the explosive growth of online service platforms, an increasing number of people and enterprises are undertaking personal and professional tasks online. In real applications such as trip planning and online marketing, planning sessions for a sequence of activities or services will enable social users to receive the optimal services, improving their experience and reducing the cost of their activities. These online platforms are heterogeneous, including different types of services with different attributes. However, the problem of session planning over heterogeneous platforms has not been studied so far. In this paper, we propose a Motivation-Aware Session Planning (MASP) framework for session planning over heterogeneous social platforms. Specifically, we first propose a novel HeterBERT model to handle the heterogeneity of items at both type and attribute levels. Then, we propose to predict user preference using the motivations behind user activities. Finally, we propose an algorithm together with its optimisations for efficient session generation. The extensive tests prove the high effectiveness and efficiency of MASP.

Social video anomaly is an observation in video streams that does not conform to a common pattern of dataset's behaviour. Social video anomaly detection plays a critical role in applications from e-commerce to e-Iearning. Traditionally, anomaly detection techniques are applied to find anomalies in video broadcasting. However, they neglect the live social video streams which contain interactive talk, speech, or lecture with audience. In this paper, we propose a generic framework for effectively online detecting Anomalies Over social Video LI ve Streaming (AOVLIS). Specifically, we propose a novel deep neural network model called Coupling Long Short-Term Memory (CLSTM) that adaptively captures the history behaviours of the presenters and audience, and their mutual interactions to predict their behaviour at next time point over streams. Then we well integrate the CLSTM with a decoder layer, and propose a new reconstruction error-based scoring function REI A to calculate the anomaly score of each video segment for anomaly detection. After that, we propose a novel model update scheme that incrementally maintains CLSTM and decoder. Moreover, we design a novel upper bound and ADaptive Optimisation Strategy (ADOS) for improving the efficiency of our solution. Extensive experiments are conducted to prove the superiority of AOVLIS.

Group recommendation over social media streams has attracted attention due to its wide applications such as e-commerce, entertainment and online news broadcasting. However, existing stream group recommendation techniques ignore the influence of user groups, which are not effective for item propagation over social networks. To address this problem, we propose a framework for Influence-aware Group Recommendation (IGR) over high-speed social streams. Specifically, we first propose a novel GroupGCN model to capture the dynamics of user attributes and interactions which maps groups and items to their embeddings. A Temporal GroupGCN-RNN-Autoencoder (TGGCN-RA) model is designed to extend GroupGCN for sequence-based tasks, enabling the prediction of group interests over time. Then, we adopt an Independent Cascade (IC) model to predict the influence propagation of social items over user groups. Extensive experiments prove the high effectiveness and efficiency of IGR.

The emergency collision avoidance capabilities of autonomous vehicles (AVs) are crucial for enhancing their active safety performance, particularly in extreme scenarios where standard methods fall short. This study introduces an Extreme Maneuver Controller (EMC) for AVs, utilizing reachability-guided reinforcement learning (RL) to address these challenging situations. By applying pseudospectral methods, we solve the minimum backward reachable tube (Min-BRT) to identify regions where conventional avoidance maneuvers are infeasible, establishing a theoretical basis for triggering extreme maneuvers. A novel controller, employing reachability-guided RL, enables vehicles to execute extreme maneuvers to escape these critical regions. During training, the value function derived from the Min-BRT solution informs the initialization of the Critic networks, enhancing training efficiency. Real-world scenario-based experimental results with actual vehicles validate that the proposed policy, effectively executes beyond-the-limit maneuvers, mitigating collision risks under emergency condition. Furthermore, these extreme maneuvers are executed with minimal deviation from the original driving objectives, ensuring a smooth and stable transition upon completion of extreme maneuvers.

Situation-awareness (SA) has been important for natural disaster management and smart decision making. Traditionally, security officers recognize disaster situations through emergency reporting with phone calls. However, due to the busy phone lines or power outages caused by disasters, traditional SA has been limited in terms of time and mitigation response, which may cause high loss in life and properties in disaster areas. Social media-based SA has been studied recently. However, existing systems are designed for events without nonconsecutive migrations over location and time. In this demo, we design HSAP, the first human-in-the-loop social media-based SA platform for effective and efficient management of disasters with complex event migrations. HSAP is designed with a number of novel techniques, including complex social event detection, summarization, and human-in-the-loop result filtering. We demonstrate the usage of HSAP via Nepal earthquake 2015.

Recently, a new type of video understanding task called Movie-Fill-in-the-Blank (MovieFIB) has attracted many research attentions. Given a pair of movie clip and description with one blank word as input, MovieFIB aims to automatically predict the blank word. Because of the advantage in processing sequence data, Long-Short Term Memory (LSTM) has been used as a key component in existing MovieFIB methods to generate representations of videos and descriptions. However, most of these methods fail to emphasize the salient parts of videos. To address this problem, in this paper we propose to use a novel LSTM network called LSTM with Linguistic gate (LSTMwL), which exploits adaptive temporal attention for MovieFIB. Specifically, we first use LSTM to produce video features, which are then used to update the text representation. Finally, we put the updated text into two opposite directional LSTMwL layers to infer the blank word. Experimental results demonstrate that our approach outperforms state-of-the-art models for MovieFIB.