Xinyu Li

Lixiang Yan, Lele Sha, Linxuan Zhao et al.

Educational technology innovations leveraging large language models (LLMs) have shown the potential to automate the laborious process of generating and analysing textual content. While various innovations have been developed to automate a range of educational tasks (e.g., question generation, feedback provision, and essay grading), there are concerns regarding the practicality and ethicality of these innovations. Such concerns may hinder future research and the adoption of LLMs-based innovations in authentic educational contexts. To address this, we conducted a systematic scoping review of 118 peer-reviewed papers published since 2017 to pinpoint the current state of research on using LLMs to automate and support educational tasks. The findings revealed 53 use cases for LLMs in automating education tasks, categorised into nine main categories: profiling/labelling, detection, grading, teaching support, prediction, knowledge representation, feedback, content generation, and recommendation. Additionally, we also identified several practical and ethical challenges, including low technological readiness, lack of replicability and transparency, and insufficient privacy and beneficence considerations. The findings were summarised into three recommendations for future studies, including updating existing innovations with state-of-the-art models (e.g., GPT-3/4), embracing the initiative of open-sourcing models/systems, and adopting a human-centred approach throughout the developmental process. As the intersection of AI and education is continuously evolving, the findings of this study can serve as an essential reference point for researchers, allowing them to leverage the strengths, learn from the limitations, and uncover potential research opportunities enabled by ChatGPT and other generative AI models.

Najmeh Sadoughi, Xinyu Li, Avijit Vajpayee et al. · amazon-science

Previous research has studied the task of segmenting cinematic videos into scenes and into narrative acts. However, these studies have overlooked the essential task of multimodal alignment and fusion for effectively and efficiently processing long-form videos (>60min). In this paper, we introduce Multimodal alignmEnt aGgregation and distillAtion (MEGA) for cinematic long-video segmentation. MEGA tackles the challenge by leveraging multiple media modalities. The method coarsely aligns inputs of variable lengths and different modalities with alignment positional encoding. To maintain temporal synchronization while reducing computation, we further introduce an enhanced bottleneck fusion layer which uses temporal alignment. Additionally, MEGA employs a novel contrastive loss to synchronize and transfer labels across modalities, enabling act segmentation from labeled synopsis sentences on video shots. Our experimental results show that MEGA outperforms state-of-the-art methods on MovieNet dataset for scene segmentation (with an Average Precision improvement of +1.19%) and on TRIPOD dataset for act segmentation (with a Total Agreement improvement of +5.51%)

Xinyu Li, Ruiyang Zhou, Zachary C. Lipton et al.

Personalized large language models (LLMs) are designed to tailor responses to individual user preferences. While Reinforcement Learning from Human Feedback (RLHF) is a commonly used framework for aligning LLMs with human preferences, vanilla RLHF assumes that all human preferences share the same distribution, preventing fine-tuned LLMs from generating personalized content when user preferences are diverse. In this work, we propose Personalized-RLHF (P-RLHF), an efficient framework that utilizes a lightweight user model to capture individual user preferences and jointly learns the user model and the personalized LLM from human feedback. P-RLHF exhibits the following three characteristics: (1) It enables an LLM to generate personalized content and scale efficiently with growing number of users. (2) It handles both explicit user preferences described as textual input and implicit user preferences encoded in the feedback data. (3) It eliminates the need for users to fully articulate their preferences, which are normally needed for prompting LLMs to generate personalized content yet are often impractical to obtain in real-world scenarios. Our experimental results show that personalized LLMs trained using P-RLHF generate responses that are more closely aligned with individual user preferences, outperforming vanilla, non-personalized RLHF and prompting-based personalization approaches across different tasks. We opensource our code at https://github.com/HumainLab/Personalized_RLHF.

Xin Guo, Xinyu Li, Renyuan Xu

This paper proposes and analyzes two new policy learning methods: regularized policy gradient (RPG) and iterative policy optimization (IPO), for a class of discounted linear-quadratic control (LQC) problems over an infinite time horizon with entropy regularization. Assuming access to the exact policy evaluation, both proposed approaches are proven to converge linearly in finding optimal policies of the regularized LQC. Moreover, the IPO method can achieve a super-linear convergence rate once it enters a local region around the optimal policy. Finally, when the optimal policy for an RL problem with a known environment is appropriately transferred as the initial policy to an RL problem with an unknown environment, the IPO method is shown to enable a super-linear convergence rate if the two environments are sufficiently close. Performances of these proposed algorithms are supported by numerical examples.

Yifu Cai, Xinyu Li, Mononito Goswami et al. · cmu

We introduce TimeSeriesGym, a scalable benchmarking framework for evaluating Artificial Intelligence (AI) agents on time series machine learning engineering challenges. Existing benchmarks lack scalability, focus narrowly on model building in well-defined settings, and evaluate only a limited set of research artifacts (e.g., CSV submission files). To make AI agent benchmarking more relevant to the practice of machine learning engineering, our framework scales along two critical dimensions. First, recognizing that effective ML engineering requires a range of diverse skills, TimeSeriesGym incorporates challenges from diverse sources spanning multiple domains and tasks. We design challenges to evaluate both isolated capabilities (including data handling, understanding research repositories, and code translation) and their combinations, and rather than addressing each challenge independently, we develop tools that support designing multiple challenges at scale. Second, we implement evaluation mechanisms for multiple research artifacts, including submission files, code, and models, using both precise numeric measures and more flexible LLM-based evaluation approaches. This dual strategy balances objective assessment with contextual judgment. Although our initial focus is on time series applications, our framework can be readily extended to other data modalities, broadly enhancing the comprehensiveness and practical utility of agentic AI evaluation. We open-source our benchmarking framework to facilitate future research on the ML engineering capabilities of AI agents.

Haofei Kuang, Yi Zhu, Zhi Zhang et al.

Contrastive learning has revolutionized self-supervised image representation learning field, and recently been adapted to video domain. One of the greatest advantages of contrastive learning is that it allows us to flexibly define powerful loss objectives as long as we can find a reasonable way to formulate positive and negative samples to contrast. However, existing approaches rely heavily on the short-range spatiotemporal salience to form clip-level contrastive signals, thus limit themselves from using global context. In this paper, we propose a new video-level contrastive learning method based on segments to formulate positive pairs. Our formulation is able to capture global context in a video, thus robust to temporal content change. We also incorporate a temporal order regularization term to enforce the inherent sequential structure of videos. Extensive experiments show that our video-level contrastive learning framework (VCLR) is able to outperform previous state-of-the-arts on five video datasets for downstream action classification, action localization and video retrieval. Code is available at https://github.com/amazon-research/video-contrastive-learning.

Seon-Ho Lee, Jue Wang, Zhikang Zhang et al. · amazon-science

As the scale of data and models for video understanding rapidly expand, handling long-form video input in transformer-based models presents a practical challenge. Rather than resorting to input sampling or token dropping, which may result in information loss, token merging shows promising results when used in collaboration with transformers. However, the application of token merging for long-form video processing is not trivial. We begin with the premise that token merging should not rely solely on the similarity of video tokens; the saliency of tokens should also be considered. To address this, we explore various video token merging strategies for long-form video classification, starting with a simple extension of image token merging, moving to region-concentrated merging, and finally proposing a learnable video token merging (VTM) algorithm that dynamically merges tokens based on their saliency. Extensive experimental results show that we achieve better or comparable performances on the LVU, COIN, and Breakfast datasets. Moreover, our approach significantly reduces memory costs by 84% and boosts throughput by approximately 6.89 times compared to baseline algorithms.

Seon-Ho Lee, Jue Wang, David Fan et al. · amazon-science

Audio Description (AD) plays a pivotal role as an application system aimed at guaranteeing accessibility in multimedia content, which provides additional narrations at suitable intervals to describe visual elements, catering specifically to the needs of visually impaired audiences. In this paper, we introduce $\mathrm{CA^3D}$, the pioneering unified Context-Aware Automatic Audio Description system that provides AD event scripts with precise locations in the long cinematic content. Specifically, $\mathrm{CA^3D}$ system consists of: 1) a Temporal Feature Enhancement Module to efficiently capture longer term dependencies, 2) an anchor-based AD event detector with feature suppression module that localizes the AD events and extracts discriminative feature for AD generation, and 3) a self-refinement module that leverages the generated output to tweak AD event boundaries from coarse to fine. Unlike conventional methods which rely on metadata and ground truth AD timestamp for AD detection and generation tasks, the proposed $\mathrm{CA^3D}$ is the first end-to-end trainable system that only uses visual cue. Extensive experiments demonstrate that the proposed $\mathrm{CA^3D}$ improves existing architectures for both AD event detection and script generation metrics, establishing the new state-of-the-art performances in the AD automation.

Xinyu Li, Qi Yao, Yuanda Wang

Garment sewing patterns are fundamental design elements that bridge the gap between design concepts and practical manufacturing. The generative modeling of sewing patterns is crucial for creating diversified garments. However, existing approaches are limited either by reliance on a single input modality or by suboptimal generation efficiency. In this work, we present GarmentDiffusion, a new generative model capable of producing centimeter-precise, vectorized 3D sewing patterns from multimodal inputs (text, image, and incomplete sewing pattern). Our method efficiently encodes 3D sewing pattern parameters into compact edge token representations, achieving a sequence length that is 10 times shorter than that of the autoregressive SewingGPT in DressCode. By employing a diffusion transformer, we simultaneously denoise all edge tokens along the temporal axis, while maintaining a constant number of denoising steps regardless of dataset-specific edge and panel statistics. With all combination of designs of our model, the sewing pattern generation speed is accelerated by 100 times compared to SewingGPT. We achieve new state-of-the-art results on DressCodeData, as well as on the largest sewing pattern dataset, namely GarmentCodeData. The project website is available at https://shenfu-research.github.io/Garment-Diffusion/.

Feng Cheng, Mingze Xu, Yuanjun Xiong et al.

We propose a memory efficient method, named Stochastic Backpropagation (SBP), for training deep neural networks on videos. It is based on the finding that gradients from incomplete execution for backpropagation can still effectively train the models with minimal accuracy loss, which attributes to the high redundancy of video. SBP keeps all forward paths but randomly and independently removes the backward paths for each network layer in each training step. It reduces the GPU memory cost by eliminating the need to cache activation values corresponding to the dropped backward paths, whose amount can be controlled by an adjustable keep-ratio. Experiments show that SBP can be applied to a wide range of models for video tasks, leading to up to 80.0% GPU memory saving and 10% training speedup with less than 1% accuracy drop on action recognition and temporal action detection.

Zhe Wang, Hao Chen, Xinyu Li et al.

Temporal action segmentation is a task to classify each frame in the video with an action label. However, it is quite expensive to annotate every frame in a large corpus of videos to construct a comprehensive supervised training dataset. Thus in this work we propose an unsupervised method, namely SSCAP, that operates on a corpus of unlabeled videos and predicts a likely set of temporal segments across the videos. SSCAP leverages Self-Supervised learning to extract distinguishable features and then applies a novel Co-occurrence Action Parsing algorithm to not only capture the correlation among sub-actions underlying the structure of activities, but also estimate the temporal path of the sub-actions in an accurate and general way. We evaluate on both classic datasets (Breakfast, 50Salads) and the emerging fine-grained action dataset (FineGym) with more complex activity structures and similar sub-actions. Results show that SSCAP achieves state-of-the-art performance on all datasets and can even outperform some weakly-supervised approaches, demonstrating its effectiveness and generalizability.

Yanyi Zhang, Xinyu Li, Chunhui Liu et al.

We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatio-temporal information via stacked attentions and provide better performance with higher efficiency. We first introduce the vanilla video transformer and show that transformer module is able to perform spatio-temporal modeling from raw pixels, but with heavy memory usage. We then present VidTr which reduces the memory cost by 3.3$\times$ while keeping the same performance. To further optimize the model, we propose the standard deviation based topK pooling for attention ($pool_{topK\_std}$), which reduces the computation by dropping non-informative features along temporal dimension. VidTr achieves state-of-the-art performance on five commonly used datasets with lower computational requirement, showing both the efficiency and effectiveness of our design. Finally, error analysis and visualization show that VidTr is especially good at predicting actions that require long-term temporal reasoning.

Jiaojiao Zhao, Yanyi Zhang, Xinyu Li et al.

We propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an off-line actor detector or hand-designed actor-positional hypotheses like proposals or anchors, we propose to directly detect an action tubelet in a video by simultaneously performing action localization and recognition from a single representation. TubeR learns a set of tubelet-queries and utilizes a tubelet-attention module to model the dynamic spatio-temporal nature of a video clip, which effectively reinforces the model capacity compared to using actor-positional hypotheses in the spatio-temporal space. For videos containing transitional states or scene changes, we propose a context aware classification head to utilize short-term and long-term context to strengthen action classification, and an action switch regression head for detecting the precise temporal action extent. TubeR directly produces action tubelets with variable lengths and even maintains good results for long video clips. TubeR outperforms the previous state-of-the-art on commonly used action detection datasets AVA, UCF101-24 and JHMDB51-21.

Chunhui Liu, Xinyu Li, Hao Chen et al.

Most action recognition solutions rely on dense sampling to precisely cover the informative temporal clip. Extensively searching temporal region is expensive for a real-world application. In this work, we focus on improving the inference efficiency of current action recognition backbones on trimmed videos, and illustrate that one action model can also cover then informative region by dropping non-informative features. We present Selective Feature Compression (SFC), an action recognition inference strategy that greatly increase model inference efficiency without any accuracy compromise. Differently from previous works that compress kernel sizes and decrease the channel dimension, we propose to compress feature flow at spatio-temporal dimension without changing any backbone parameters. Our experiments on Kinetics-400, UCF101 and ActivityNet show that SFC is able to reduce inference speed by 6-7x and memory usage by 5-6x compared with the commonly used 30 crops dense sampling procedure, while also slightly improving Top1 Accuracy. We thoroughly quantitatively and qualitatively evaluate SFC and all its components and show how does SFC learn to attend to important video regions and to drop temporal features that are uninformative for the task of action recognition.

Xinyu Li, Chunhui Liu, Bing Shuai et al.

In the world of action recognition research, one primary focus has been on how to construct and train networks to model the spatial-temporal volume of an input video. These methods typically uniformly sample a segment of an input clip (along the temporal dimension). However, not all parts of a video are equally important to determine the action in the clip. In this work, we focus instead on learning where to extract features, so as to focus on the most informative parts of the video. We propose a method called the non-uniform temporal aggregation (NUTA), which aggregates features only from informative temporal segments. We also introduce a synchronization method that allows our NUTA features to be temporally aligned with traditional uniformly sampled video features, so that both local and clip-level features can be combined. Our model has achieved state-of-the-art performance on four widely used large-scale action-recognition datasets (Kinetics400, Kinetics700, Something-something V2 and Charades). In addition, we have created a visualization to illustrate how the proposed NUTA method selects only the most relevant parts of a video clip.

Yi Zhu, Xinyu Li, Chunhui Liu et al.

Video action recognition is one of the representative tasks for video understanding. Over the last decade, we have witnessed great advancements in video action recognition thanks to the emergence of deep learning. But we also encountered new challenges, including modeling long-range temporal information in videos, high computation costs, and incomparable results due to datasets and evaluation protocol variances. In this paper, we provide a comprehensive survey of over 200 existing papers on deep learning for video action recognition. We first introduce the 17 video action recognition datasets that influenced the design of models. Then we present video action recognition models in chronological order: starting with early attempts at adapting deep learning, then to the two-stream networks, followed by the adoption of 3D convolutional kernels, and finally to the recent compute-efficient models. In addition, we benchmark popular methods on several representative datasets and release code for reproducibility. In the end, we discuss open problems and shed light on opportunities for video action recognition to facilitate new research ideas.

Yanyi Zhang, Xinyu Li, Ivan Marsic

Multi-label activity recognition is designed for recognizing multiple activities that are performed simultaneously or sequentially in each video. Most recent activity recognition networks focus on single-activities, that assume only one activity in each video. These networks extract shared features for all the activities, which are not designed for multi-label activities. We introduce an approach to multi-label activity recognition that extracts independent feature descriptors for each activity and learns activity correlations. This structure can be trained end-to-end and plugged into any existing network structures for video classification. Our method outperformed state-of-the-art approaches on four multi-label activity recognition datasets. To better understand the activity-specific features that the system generated, we visualized these activity-specific features in the Charades dataset.

Xinyu Li, Bing Shuai, Joseph Tighe

Many current activity recognition models use 3D convolutional neural networks (e.g. I3D, I3D-NL) to generate local spatial-temporal features. However, such features do not encode clip-level ordered temporal information. In this paper, we introduce a channel independent directional convolution (CIDC) operation, which learns to model the temporal evolution among local features. By applying multiple CIDC units we construct a light-weight network that models the clip-level temporal evolution across multiple spatial scales. Our CIDC network can be attached to any activity recognition backbone network. We evaluate our method on four popular activity recognition datasets and consistently improve upon state-of-the-art techniques. We further visualize the activation map of our CIDC network and show that it is able to focus on more meaningful, action related parts of the frame.

Dongfang Li, Yifei Yu, Qingcai Chen et al.

Recently, pre-trained models have been the dominant paradigm in natural language processing. They achieved remarkable state-of-the-art performance across a wide range of related tasks, such as textual entailment, natural language inference, question answering, etc. BERT, proposed by Devlin et.al., has achieved a better marked result in GLUE leaderboard with a deep transformer architecture. Despite its soaring popularity, however, BERT has not yet been applied to answer selection. This task is different from others with a few nuances: first, modeling the relevance and correctness of candidates matters compared to semantic relatedness and syntactic structure; second, the length of an answer may be different from other candidates and questions. In this paper. we are the first to explore the performance of fine-tuning BERT for answer selection. We achieved STOA results across five popular datasets, demonstrating the success of pre-trained models in this task.

Xinyu Li, Venkata Chebiyyam, Katrin Kirchhoff

Environmental sound classification systems often do not perform robustly across different sound classification tasks and audio signals of varying temporal structures. We introduce a multi-stream convolutional neural network with temporal attention that addresses these problems. The network relies on three input streams consisting of raw audio and spectral features and utilizes a temporal attention function computed from energy changes over time. Training and classification utilizes decision fusion and data augmentation techniques that incorporate uncertainty. We evaluate this network on three commonly used data sets for environmental sound and audio scene classification and achieve new state-of-the-art performance without any changes in network architecture or front-end preprocessing, thus demonstrating better generalizability.

Yanyi Zhang, Xinyu Li, Kaixiang Huang et al.

We present a system for concurrent activity recognition. To extract features associated with different activities, we propose a feature-to-activity attention that maps the extracted global features to sub-features associated with individual activities. To model the temporal associations of individual activities, we propose a transformer-network encoder that models independent temporal associations for each activity. To make the concurrent activity prediction aware of the potential associations between activities, we propose self-attention with an association mask. Our system achieved state-of-the-art or comparable performance on three commonly used concurrent activity detection datasets. Our visualizations demonstrate that our system is able to locate the important spatial-temporal features for final decision making. We also showed that our system can be applied to general multilabel classification problems.

Yue Gu, Kangning Yang, Shiyu Fu et al.

Multimodal affective computing, learning to recognize and interpret human affects and subjective information from multiple data sources, is still challenging because: (i) it is hard to extract informative features to represent human affects from heterogeneous inputs; (ii) current fusion strategies only fuse different modalities at abstract level, ignoring time-dependent interactions between modalities. Addressing such issues, we introduce a hierarchical multimodal architecture with attention and word-level fusion to classify utter-ance-level sentiment and emotion from text and audio data. Our introduced model outperforms the state-of-the-art approaches on published datasets and we demonstrated that our model is able to visualize and interpret the synchronized attention over modalities.

Xinyu Li, Yanyi Zhang, Jianyu Zhang et al.

Process modeling and understanding are fundamental for advanced human-computer interfaces and automation systems. Most recent research has focused on activity recognition, but little has been done on sensor-based detection of process progress. We introduce a real-time, sensor-based system for modeling, recognizing and estimating the progress of a work process. We implemented a multimodal deep learning structure to extract the relevant spatio-temporal features from multiple sensory inputs and used a novel deep regression structure for overall completeness estimation. Using process completeness estimation with a Gaussian mixture model, our system can predict the phase for sequential processes. The performance speed, calculated using completeness estimation, allows online estimation of the remaining time. To train our system, we introduced a novel rectified hyperbolic tangent (rtanh) activation function and conditional loss. Our system was tested on data obtained from the medical process (trauma resuscitation) and sports events (Olympic swimming competition). Our system outperformed the existing trauma-resuscitation phase detectors with a phase detection accuracy of over 86%, an F1-score of 0.67, a completeness estimation error of under 12.6%, and a remaining-time estimation error of less than 7.5 minutes. For the Olympic swimming dataset, our system achieved an accuracy of 88%, an F1-score of 0.58, a completeness estimation error of 6.3% and a remaining-time estimation error of 2.9 minutes.

Xinyu Li, Yanyi Zhang, Jianyu Zhang et al.

We introduce a system that recognizes concurrent activities from real-world data captured by multiple sensors of different types. The recognition is achieved in two steps. First, we extract spatial and temporal features from the multimodal data. We feed each datatype into a convolutional neural network that extracts spatial features, followed by a long-short term memory network that extracts temporal information in the sensory data. The extracted features are then fused for decision making in the second step. Second, we achieve concurrent activity recognition with a single classifier that encodes a binary output vector in which elements indicate whether the corresponding activity types are currently in progress. We tested our system with three datasets from different domains recorded using different sensors and achieved performance comparable to existing systems designed specifically for those domains. Our system is the first to address the concurrent activity recognition with multisensory data using a single model, which is scalable, simple to train and easy to deploy.