Du Q. Huynh

Qiang Sun, Sirui Li, Du Huynh et al.

Question answering over temporal knowledge graphs (TKGs) is crucial for understanding evolving facts and relationships, yet its development is hindered by limited datasets and difficulties in generating custom QA pairs. We propose a novel categorization framework based on timeline-context relationships, along with \textbf{TimelineKGQA}, a universal temporal QA generator applicable to any TKGs. The code is available at: \url{https://github.com/PascalSun/TimelineKGQA} as an open source Python package.

Qiang Sun, Sirui Li, Tingting Bi et al.

Acquiring structured data from domain-specific, image-based documents such as scanned reports is crucial for many downstream tasks but remains challenging due to document variability. Many of these documents exist as images rather than as machine-readable text, which requires human annotation to train automated extraction systems. We present DocSpiral, the first Human-in-the-Spiral assistive document annotation platform, designed to address the challenge of extracting structured information from domain-specific, image-based document collections. Our spiral design establishes an iterative cycle in which human annotations train models that progressively require less manual intervention. DocSpiral integrates document format normalization, comprehensive annotation interfaces, evaluation metrics dashboard, and API endpoints for the development of AI / ML models into a unified workflow. Experiments demonstrate that our framework reduces annotation time by at least 41\% while showing consistent performance gains across three iterations during model training. By making this annotation platform freely accessible, we aim to lower barriers to AI/ML models development in document processing, facilitating the adoption of large language models in image-based, document-intensive fields such as geoscience and healthcare. The system is freely available at: https://app.ai4wa.com. The demonstration video is available: https://app.ai4wa.com/docs/docspiral/demo.

Areej Alsini, Du Q. Huynh, Amitava Datta

Automatic evaluation of hashtag recommendation models is a fundamental task in many online social network systems. In the traditional evaluation method, the recommended hashtags from an algorithm are firstly compared with the ground truth hashtags for exact correspondences. The number of exact matches is then used to calculate the hit rate, hit ratio, precision, recall, or F1-score. This way of evaluating hashtag similarities is inadequate as it ignores the semantic correlation between the recommended and ground truth hashtags. To tackle this problem, we propose a novel semantic evaluation framework for hashtag recommendation, called #REval. This framework includes an internal module referred to as BERTag, which automatically learns the hashtag embeddings. We investigate on how the #REval framework performs under different word embedding methods and different numbers of synonyms and hashtags in the recommendation using our proposed #REval-hit-ratio measure. Our experiments of the proposed framework on three large datasets show that #REval gave more meaningful hashtag synonyms for hashtag recommendation evaluation. Our analysis also highlights the sensitivity of the framework to the word embedding technique, with #REval based on BERTag more superior over #REval based on FastText and Word2Vec.

Hao Xue, Du Q. Huynh, Mark Reynolds

Pedestrian trajectory prediction is valuable for understanding human motion behaviors and it is challenging because of the social influence from other pedestrians, the scene constraints and the multimodal possibilities of predicted trajectories. Most existing methods only focus on two of the above three key elements. In order to jointly consider all these elements, we propose a novel trajectory prediction method named Scene Gated Social Graph (SGSG). In the proposed SGSG, dynamic graphs are used to describe the social relationship among pedestrians. The social and scene influences are taken into account through the scene gated social graph features which combine the encoded social graph features and semantic scene features. In addition, a VAE module is incorporated to learn the scene gated social feature and sample latent variables for generating multiple trajectories that are socially and environmentally acceptable. We compare our SGSG against twenty state-of-the-art pedestrian trajectory prediction methods and the results show that the proposed method achieves superior performance on two widely used trajectory prediction benchmarks.

Areej Alsini, Du Q. Huynh, Amitava Datta

Hashtag recommendation is a crucial task, especially with an increase of interest in using social media platforms such as Twitter in the last decade. Hashtag recommendation systems automatically suggest hashtags to a user while writing a tweet. Most of the research in the area of hashtag recommendation have used classical metrics such as hit rate, precision, recall, and F1-score to measure the accuracy of hashtag recommendation systems. These metrics are based on the exact match of the recommended hashtags with their corresponding ground truth. However, it is not clear how adequate these metrics to evaluate hashtag recommendation. The research question that we are interested in seeking an answer is: are these metrics adequate for evaluating hashtag recommendation systems when the numbers of ground truth hashtags in tweets are highly variable? In this paper, we propose a new metric which we call hit ratio for hashtag recommendation. Extensive evaluation through hypothetical examples and real-world application across a range of hashtag recommendation models indicate that the hit ratio is a useful metric. A comparison of hit ratio with the classical evaluation metrics reveals their limitations.

Hao Xue, Du. Q. Huynh, Mark Reynolds

Pedestrian trajectory prediction is a challenging task as there are three properties of human movement behaviors which need to be addressed, namely, the social influence from other pedestrians, the scene constraints, and the multimodal (multiroute) nature of predictions. Although existing methods have explored these key properties, the prediction process of these methods is autoregressive. This means they can only predict future locations sequentially. In this paper, we present NAP, a non-autoregressive method for trajectory prediction. Our method comprises specifically designed feature encoders and a latent variable generator to handle the three properties above. It also has a time-agnostic context generator and a time-specific context generator for non-autoregressive prediction. Through extensive experiments that compare NAP against several recent methods, we show that NAP has state-of-the-art trajectory prediction performance.

Lei Wang, Du Q. Huynh, Moussa Reda Mansour

From video streaming to security and surveillance applications, video data play an important role in our daily living today. However, managing a large amount of video data and retrieving the most useful information for the user remain a challenging task. In this paper, we propose a novel video classification system that would benefit the scene understanding task. We define our classification problem as classifying background and foreground motions using the same feature representation for outdoor scenes. This means that the feature representation needs to be robust enough and adaptable to different classification tasks. We propose a lightweight Loss Switching Fusion Network (LSFNet) for the fusion of spatiotemporal descriptors and a similarity search scheme with soft voting to boost the classification performance. The proposed system has a variety of potential applications such as content-based video clustering, video filtering, etc. Evaluation results on two private industry datasets show that our system is robust in both classifying different background motions and detecting human motions from these background motions.

Lei Wang, Piotr Koniusz, Du Q. Huynh

In this paper, we revive the use of old-fashioned handcrafted video representations for action recognition and put new life into these techniques via a CNN-based hallucination step. Despite of the use of RGB and optical flow frames, the I3D model (amongst others) thrives on combining its output with the Improved Dense Trajectory (IDT) and extracted with its low-level video descriptors encoded via Bag-of-Words (BoW) and Fisher Vectors (FV). Such a fusion of CNNs and handcrafted representations is time-consuming due to pre-processing, descriptor extraction, encoding and tuning parameters. Thus, we propose an end-to-end trainable network with streams which learn the IDT-based BoW/FV representations at the training stage and are simple to integrate with the I3D model. Specifically, each stream takes I3D feature maps ahead of the last 1D conv. layer and learns to `translate' these maps to BoW/FV representations. Thus, our model can hallucinate and use such synthesized BoW/FV representations at the testing stage. We show that even features of the entire I3D optical flow stream can be hallucinated thus simplifying the pipeline. Our model saves 20-55h of computations and yields state-of-the-art results on four publicly available datasets.

Hossein Rahmani, Arif Mahmood, Du Huynh et al.

Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which are viewpoint dependent. In contrast, we directly process pointclouds for cross-view action recognition from unknown and unseen views. We propose the Histogram of Oriented Principal Components (HOPC) descriptor that is robust to noise, viewpoint, scale and action speed variations. At a 3D point, HOPC is computed by projecting the three scaled eigenvectors of the pointcloud within its local spatio-temporal support volume onto the vertices of a regular dodecahedron. HOPC is also used for the detection of Spatio-Temporal Keypoints (STK) in 3D pointcloud sequences so that view-invariant STK descriptors (or Local HOPC descriptors) at these key locations only are used for action recognition. We also propose a global descriptor computed from the normalized spatio-temporal distribution of STKs in 4-D, which we refer to as STK-D. We have evaluated the performance of our proposed descriptors against nine existing techniques on two cross-view and three single-view human action recognition datasets. The Experimental results show that our techniques provide significant improvement over state-of-the-art methods.

Hossein Rahmani, Arif Mahmood, Du Huynh et al.

We propose an action classification algorithm which uses Locality-constrained Linear Coding (LLC) to capture discriminative information of human body variations in each spatiotemporal subsequence of a video sequence. Our proposed method divides the input video into equally spaced overlapping spatiotemporal subsequences, each of which is decomposed into blocks and then cells. We use the Histogram of Oriented Gradient (HOG3D) feature to encode the information in each cell. We justify the use of LLC for encoding the block descriptor by demonstrating its superiority over Sparse Coding (SC). Our sequence descriptor is obtained via a logistic regression classifier with L2 regularization. We evaluate and compare our algorithm with ten state-of-the-art algorithms on five benchmark datasets. Experimental results show that, on average, our algorithm gives better accuracy than these ten algorithms.

Hossein Rahmani, Arif Mahmood, Du Q. Huynh et al.

Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which change significantly with viewpoint. In contrast, we directly process the pointclouds and propose a new technique for action recognition which is more robust to noise, action speed and viewpoint variations. Our technique consists of a novel descriptor and keypoint detection algorithm. The proposed descriptor is extracted at a point by encoding the Histogram of Oriented Principal Components (HOPC) within an adaptive spatio-temporal support volume around that point. Based on this descriptor, we present a novel method to detect Spatio-Temporal Key-Points (STKPs) in 3D pointcloud sequences. Experimental results show that the proposed descriptor and STKP detector outperform state-of-the-art algorithms on three benchmark human activity datasets. We also introduce a new multiview public dataset and show the robustness of our proposed method to viewpoint variations.