Junxiao Shen

Yunze Liu, Chi-Hao Wu, Enmin Zhou et al.

Unified multimodal embedding spaces have become the standard interface for cross-modal retrieval and multimodal RAG, and recent audio-video-text (AVT) encoders extend this setting to three modalities. Such encoders can produce a joint (T,V,A) embedding whenever all three modalities are available, but standard pairwise InfoNCE objectives leave this signal unused during training. We close this gap with fusion-as-teacher distillation, which treats a stop-gradient copy of the fused embedding as a teacher signal for the single-modal embeddings, paired with a Tuple-InfoNCE term that supervises the fused embedding directly. We instantiate this objective as OmniRetriever-7B. Across six zero-shot retrieval benchmarks, OmniRetriever-7B surpasses the closed-source Gemini Embedding 2 by 13.3-18.0 R@1 on Clotho and SoundDescs, and reaches the contemporary zero-shot specialist band of open video-text encoders on MSR-VTT and MSVD. To stress-test joint representations, we further release OmniRetriever-Bench, a 12-direction AVT retrieval benchmark totaling 3782 triples; on it OmniRetriever-7B attains AVG-all 34.84, improving over Gemini Embedding 2 by 1.72 and over the best prior open-source AVT method by 8.03.

Xuhai Xu, Mengjie Yu, Tanya R. Jonker et al.

Explainable AI (XAI) has established itself as an important component of AI-driven interactive systems. With Augmented Reality (AR) becoming more integrated in daily lives, the role of XAI also becomes essential in AR because end-users will frequently interact with intelligent services. However, it is unclear how to design effective XAI experiences for AR. We propose XAIR, a design framework that addresses "when", "what", and "how" to provide explanations of AI output in AR. The framework was based on a multi-disciplinary literature review of XAI and HCI research, a large-scale survey probing 500+ end-users' preferences for AR-based explanations, and three workshops with 12 experts collecting their insights about XAI design in AR. XAIR's utility and effectiveness was verified via a study with 10 designers and another study with 12 end-users. XAIR can provide guidelines for designers, inspiring them to identify new design opportunities and achieve effective XAI designs in AR.

Xinyi Wang, Angeliki Katsenou, Junxiao Shen et al.

Short-form video poses new challenges to the quality assessment of user-generated content (UGC) due to its complex generation pipeline, rapid content variation, and mixed distortions. To address this challenge, we propose an end-to-end video quality assessment (VQA) framework that employs a dense visual encoder based on CLIP, and incorporates compression priors derived from the frequency domain to generate artifact- and structure-aware weight maps for feature aggregation. By explicitly decomposing artifact, structure, and original visual feature branches and adaptively fusing them over time through a learned gating module, the proposed method achieves accurate and efficient quality prediction. Experimental results show that our method achieves strong performance on short-form video datasets in terms of average rank and linear correlation (SRCC: 0.736, PLCC: 0.787), while maintaining efficient inference runtime. The code and additional results are available at: https://github.com/xinyiW915/FGSVQA.

Xinyi Wang, Angeliki Katsenou, Junxiao Shen et al.

The prevalence of user-generated content (UGC) on platforms such as YouTube and TikTok has rendered no-reference (NR) perceptual video quality assessment (VQA) vital for optimizing video delivery. Nonetheless, the characteristics of non-professional acquisition and the subsequent transcoding of UGC video on sharing platforms present significant challenges for NR-VQA. Although NR-VQA models attempt to infer mean opinion scores (MOS), their modeling of subjective scores for compressed content remains limited due to the absence of fine-grained perceptual annotations of artifact types. To address these challenges, we propose CAMP-VQA, a novel NR-VQA framework that exploits the semantic understanding capabilities of large vision-language models. Our approach introduces a quality-aware prompting mechanism that integrates video metadata (e.g., resolution, frame rate, bitrate) with key fragments extracted from inter-frame variations to guide the BLIP-2 pretraining approach in generating fine-grained quality captions. A unified architecture has been designed to model perceptual quality across three dimensions: semantic alignment, temporal characteristics, and spatial characteristics. These multimodal features are extracted and fused, then regressed to video quality scores. Extensive experiments on a wide variety of UGC datasets demonstrate that our model consistently outperforms existing NR-VQA methods, achieving improved accuracy without the need for costly manual fine-grained annotations. Our method achieves the best performance in terms of average rank and linear correlation (SRCC: 0.928, PLCC: 0.938) compared to state-of-the-art methods. The source code and trained models, along with a user-friendly demo, are available at: https://github.com/xinyiW915/CAMP-VQA.

Peiran Wu, Yunze Liu, Chi-Hao Wu et al.

Omnimodal large language models enable unified audio video understanding, but long joint token sequences make inference costly, and existing benchmarks do not fully isolate audio visual association in noisy user generated videos. We introduce UGC-AVQA, a public UGC benchmark with 1,000 videos and 4,816 QA pairs, where an audio removal test ensures that benchmark questions require both acoustic and visual evidence. To reduce inference cost, we propose OMAC, a training free plug in compression method that preserves salient visual memory and temporally grounded audio anchors. To further make compact models robust to compressed inputs, we introduce O-MARC, a compression distillation framework for learning with memory compressed multimodal contexts. On Qwen2.5-Omni-3B, O-MARC improves the average score across four benchmarks to 45.8, outperforming full token inference at 44.1 and OmniZip at 41.0. OMAC also keeps inference efficient, reducing latency by 34.6\% (1.53$\times$ speedup) and memory by 34.7\% compared with full token inference.

Junxiao Shen, John Dudley, Per Ola Kristensson

We depend on our own memory to encode, store, and retrieve our experiences. However, memory lapses can occur. One promising avenue for achieving memory augmentation is through the use of augmented reality head-mounted displays to capture and preserve egocentric videos, a practice commonly referred to as lifelogging. However, a significant challenge arises from the sheer volume of video data generated through lifelogging, as the current technology lacks the capability to encode and store such large amounts of data efficiently. Further, retrieving specific information from extensive video archives requires substantial computational power, further complicating the task of quickly accessing desired content. To address these challenges, we propose a memory augmentation agent that involves leveraging natural language encoding for video data and storing them in a vector database. This approach harnesses the power of large vision language models to perform the language encoding process. Additionally, we propose using large language models to facilitate natural language querying. Our agent underwent extensive evaluation using the QA-Ego4D dataset and achieved state-of-the-art results with a BLEU score of 8.3, outperforming conventional machine learning models that scored between 3.4 and 5.8. Additionally, we conducted a user study in which participants interacted with the human memory augmentation agent through episodic memory and open-ended questions. The results of this study show that the agent results in significantly better recall performance on episodic memory tasks compared to human participants. The results also highlight the agent's practical applicability and user acceptance.

Junxiao Shen, John J. Dudley, Jingyao Zheng et al.

Text entry is an essential task in our day-to-day digital interactions. Numerous intelligent features have been developed to streamline this process, making text entry more effective, efficient, and fluid. These improvements include sentence prediction and user personalization. However, as deep learning-based language models become the norm for these advanced features, the necessity for data collection and model fine-tuning increases. These challenges can be mitigated by harnessing the in-context learning capability of large language models such as GPT-3.5. This unique feature allows the language model to acquire new skills through prompts, eliminating the need for data collection and fine-tuning. Consequently, large language models can learn various text prediction techniques. We initially showed that, for a sentence prediction task, merely prompting GPT-3.5 surpassed a GPT-2 backed system and is comparable with a fine-tuned GPT-3.5 model, with the latter two methods requiring costly data collection, fine-tuning and post-processing. However, the task of prompting large language models to specialize in specific text prediction tasks can be challenging, particularly for designers without expertise in prompt engineering. To address this, we introduce Promptor, a conversational prompt generation agent designed to engage proactively with designers. Promptor can automatically generate complex prompts tailored to meet specific needs, thus offering a solution to this challenge. We conducted a user study involving 24 participants creating prompts for three intelligent text entry tasks, half of the participants used Promptor while the other half designed prompts themselves. The results show that Promptor-designed prompts result in a 35% increase in similarity and 22% in coherence over those by designers.

Yunze Liu, Peiran Wu, Cheng Liang et al.

Recent Mamba-based architectures for video understanding demonstrate promising computational efficiency and competitive performance, yet struggle with overfitting issues that hinder their scalability. To overcome this challenge, we introduce VideoMAP, a Hybrid Mamba-Transformer framework featuring a novel pre-training approach. VideoMAP uses a 4:1 Mamba-to-Transformer ratio, effectively balancing computational cost and model capacity. This architecture, combined with our proposed frame-wise masked autoregressive pre-training strategy, delivers significant performance gains when scaling to larger models. Additionally, VideoMAP exhibits impressive sample efficiency, significantly outperforming existing methods with less training data. Experiments show that VideoMAP outperforms existing models across various datasets, including Kinetics-400, Something-Something V2, Breakfast, and COIN. Furthermore, we demonstrate the potential of VideoMAP as a visual encoder for multimodal large language models, highlighting its ability to reduce memory usage and enable the processing of longer video sequences. The code is open-source at https://github.com/yunzeliu/MAP

Xinyi Zheng, Yunze Liu, Chi-Hao Wu et al.

We present SpatialMem, a memory-centric system that unifies 3D geometry, semantics, and language into a single, queryable representation. Starting from casually captured egocentric RGB video, SpatialMem reconstructs metrically scaled indoor environments, detects structural 3D anchors (walls, doors, windows) as the first-layer scaffold, and populates a hierarchical memory with open-vocabulary object nodes -- linking evidence patches, visual embeddings, and two-layer textual descriptions to 3D coordinates -- for compact storage and fast retrieval. This design enables interpretable reasoning over spatial relations (e.g., distance, direction, visibility) and supports downstream tasks such as language-guided navigation and object retrieval without specialized sensors. Experiments across three real-life indoor scenes demonstrate that SpatialMem maintains strong anchor-description-level navigation completion and hierarchical retrieval accuracy under increasing clutter and occlusion, offering an efficient and extensible framework for embodied spatial intelligence.

Xinyi Zheng, Steve Zhang, Weizhe Lin et al.

Current state-of-the-art 3D reconstruction models face limitations in building extra-large scale outdoor scenes, primarily due to the lack of sufficiently large-scale and detailed datasets. In this paper, we present a extra-large fine-grained dataset with 10 billion points composed of 41,006 drone-captured high-resolution aerial images, covering 20 diverse and culturally significant scenes from worldwide locations such as Cambridge Uni main buildings, the Pyramids, and the Forbidden City Palace. Compared to existing datasets, ours offers significantly larger scale and higher detail, uniquely suited for fine-grained 3D applications. Each scene contains an accurate spatial layout and comprehensive structural information, supporting detailed 3D reconstruction tasks. By reconstructing environments using these detailed images, our dataset supports multiple applications, including outputs in the widely adopted COLMAP format, establishing a novel benchmark for evaluating state-of-the-art large-scale Gaussian Splatting methods.The dataset's flexibility encourages innovations and supports model plug-ins, paving the way for future 3D breakthroughs. All datasets and code will be open-sourced for community use.

Weizhe Lin, Junxiao Shen

The rapid evolution of artificial intelligence, especially through multi-modal large language models, has redefined user interactions, enabling responses that are contextually rich and human-like. As AI becomes an integral part of daily life, a new frontier has emerged: developing systems that not only understand spatial and sensory data but also interpret temporal contexts to build long-term, personalized memories. This report introduces Lucia, an open-source Temporal Computing Platform designed to enhance human cognition by capturing and utilizing continuous contextual memory. Lucia introduces a lightweight, wearable device that excels in both comfort and real-time data accessibility, distinguishing itself from existing devices that typically prioritize either wearability or perceptual capabilities alone. By recording and interpreting daily activities over time, Lucia enables users to access a robust temporal memory, enhancing cognitive processes such as decision-making and memory recall.

Peiran Wu, Yunze Liu, Miao Liu et al.

Humans excel at spatial-temporal reasoning, effortlessly interpreting dynamic visual events from an egocentric viewpoint. However, whether multimodal large language models (MLLMs) can similarly understand the 4D world remains uncertain. This paper explores multimodal spatial-temporal reasoning from an egocentric perspective, aiming to equip MLLMs with human-like reasoning capabilities. To support this objective, we introduce \textbf{Ego-ST Bench}, a novel benchmark containing over 5,000 question-answer pairs across four categories, systematically evaluating spatial, temporal, and integrated spatial-temporal reasoning. Additionally, we propose \textbf{ST-R1} training paradigm, a video-based reasoning model that incorporates reverse thinking into its reinforcement learning process, significantly enhancing performance. We combine long-chain-of-thought (long-CoT) supervised fine-tuning with Group Relative Policy Optimization (GRPO) reinforcement learning, achieving notable improvements with limited high-quality data. Ego-ST Bench and ST-R1 provide valuable insights and resources for advancing video-based spatial-temporal reasoning research.

Zihong He, Weizhe Lin, Hao Zheng et al.

With the rapid advancement of AI systems, their abilities to store, retrieve, and utilize information over the long term - referred to as long-term memory - have become increasingly significant. These capabilities are crucial for enhancing the performance of AI systems across a wide range of tasks. However, there is currently no comprehensive survey that systematically investigates AI's long-term memory capabilities, formulates a theoretical framework, and inspires the development of next-generation AI long-term memory systems. This paper begins by introducing the mechanisms of human long-term memory, then explores AI long-term memory mechanisms, establishing a mapping between the two. Based on the mapping relationships identified, we extend the current cognitive architectures and propose the Cognitive Architecture of Self-Adaptive Long-term Memory (SALM). SALM provides a theoretical framework for the practice of AI long-term memory and holds potential for guiding the creation of next-generation long-term memory driven AI systems. Finally, we delve into the future directions and application prospects of AI long-term memory.

Wenqi Zhou, Kai Cao, Hao Zheng et al.

Long-form egocentric video understanding provides rich contextual information and unique insights into long-term human behaviors, holding significant potential for applications in embodied intelligence, long-term activity analysis, and personalized assistive technologies. However, existing benchmark datasets primarily focus on single, short (\eg, minutes to tens of minutes) to moderately long videos, leaving a substantial gap in evaluating extensive, ultra-long egocentric video recordings. To address this, we introduce X-LeBench, a novel benchmark dataset meticulously designed to fill this gap by focusing on tasks requiring a comprehensive understanding of extremely long egocentric video recordings. Our X-LeBench develops a life-logging simulation pipeline that produces realistic, coherent daily plans aligned with real-world video data. This approach enables the flexible integration of synthetic daily plans with real-world footage from Ego4D-a massive-scale egocentric video dataset covers a wide range of daily life scenarios-resulting in 432 simulated video life logs spanning from 23 minutes to 16.4 hours. The evaluations of several baseline systems and multimodal large language models (MLLMs) reveal their poor performance across the board, highlighting the inherent challenges of long-form egocentric video understanding, such as temporal localization and reasoning, context aggregation, and memory retention, and underscoring the need for more advanced models.

Peiran Wu, Yunze Liu, Zhengdong Zhu et al.

Real-world user-generated videos, especially on platforms like TikTok, often feature rich and intertwined audio visual content. However, existing video captioning benchmarks and models remain predominantly visual centric, overlooking the crucial role of audio in conveying scene dynamics, speaker intent, and narrative context. This lack of omni datasets and lightweight, capable models hampers progress in fine grained, multimodal video understanding. To address these challenges, we introduce UGC-VideoCap, a new benchmark and model framework specifically designed for detailed omnimodal captioning of short form user-generated videos. Unlike prior datasets, UGC-VideoCap emphasizes balanced integration of audio and visual modalities, featuring 1000 TikTok videos annotated through a structured three stage human-in-the-loop pipeline covering audio only, visual only, and joint audio visual semantics. The benchmark also includes 4000 carefully crafted QA pairs probing both unimodal and cross modal understanding. Alongside the dataset, we propose UGC-VideoCaptioner(3B), a 3B parameter captioning model distilled from Gemini 2.5 Flash. Using a novel two-stage training strategy supervised fine tuning followed by Group Relative Policy Optimization (GRPO), our approach enables efficient adaptation from limited data while maintaining competitive performance. Together, our benchmark and model offer a high-quality foundation and a data-efficient solution for advancing omnimodal video captioning in unconstrained real-world UGC settings.

Peiran Wu, Zhuorui Yu, Yunze Liu et al.

The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs) still face heavy computational costs when extended from images to videos due to high frame rates and long durations. Token compression is a promising solution, yet most existing training-free methods cause information loss and performance degradation. To overcome this, we propose \textbf{Memory-Augmented Reinforcement Learning-based Token Compression (MARC)}, which integrates structured retrieval and RL-based distillation. MARC adopts a \textit{retrieve-then-compress} strategy using a \textbf{Visual Memory Retriever (VMR)} to select key clips and a \textbf{Compression Group Relative Policy Optimization (C-GRPO)} framework to distil reasoning ability from a teacher to a student model. Experiments on six video benchmarks show that MARC achieves near-baseline accuracy using only one frame's tokens -- reducing visual tokens by \textbf{95\%}, GPU memory by \textbf{72\%}, and latency by \textbf{23.9\%}. This demonstrates its potential for efficient, real-time video understanding in resource-constrained settings such as video QA, surveillance, and autonomous driving.

Zihan Ding, Xinyi Wang, Junlong Chen et al.

Creators struggle to edit long-form, narrative-rich videos not because of UI complexity, but due to the cognitive demands of searching, storyboarding, and sequencing hours of footage. Existing transcript- or embedding-based methods fall short for creative workflows, as models struggle to track characters, infer motivations, and connect dispersed events. We present a prompt-driven, modular editing system that helps creators restructure multi-hour content through free-form prompts rather than timelines. At its core is a semantic indexing pipeline that builds a global narrative via temporal segmentation, guided memory compression, and cross-granularity fusion, producing interpretable traces of plot, dialogue, emotion, and context. Users receive cinematic edits while optionally refining transparent intermediate outputs. Evaluated on 400+ videos with expert ratings, QA, and preference studies, our system scales prompt-driven editing, preserves narrative coherence, and balances automation with creator control.

Likun Zhang, Sicheng Yang, Zhuo Wang et al.

In this paper, we present an end-to-end automated motion recognition (AutoMR) pipeline designed for multimodal datasets. The proposed framework seamlessly integrates data preprocessing, model training, hyperparameter tuning, and evaluation, enabling robust performance across diverse scenarios. Our approach addresses two primary challenges: 1) variability in sensor data formats and parameters across datasets, which traditionally requires task-specific machine learning implementations, and 2) the complexity and time consumption of hyperparameter tuning for optimal model performance. Our library features an all-in-one solution incorporating QuartzNet as the core model, automated hyperparameter tuning, and comprehensive metrics tracking. Extensive experiments demonstrate its effectiveness on 10 diverse datasets, achieving state-of-the-art performance. This work lays a solid foundation for deploying motion-capture solutions across varied real-world applications.

Boxuan Zhu, Sicheng Yang, Zhuo Wang et al.

Gesture recognition in resource-constrained scenarios faces significant challenges in achieving high accuracy and low latency. The streaming gesture recognition framework, Duo Streamers, proposed in this paper, addresses these challenges through a three-stage sparse recognition mechanism, an RNN-lite model with an external hidden state, and specialized training and post-processing pipelines, thereby making innovative progress in real-time performance and lightweight design. Experimental results show that Duo Streamers matches mainstream methods in accuracy metrics, while reducing the real-time factor by approximately 92.3%, i.e., delivering a nearly 13-fold speedup. In addition, the framework shrinks parameter counts to 1/38 (idle state) and 1/9 (busy state) compared to mainstream models. In summary, Duo Streamers not only offers an efficient and practical solution for streaming gesture recognition in resource-constrained devices but also lays a solid foundation for extended applications in multimodal and diverse scenarios.

Junxiao Shen, Xuhai Xu, Ran Tan et al.

Training a real-time gesture recognition model heavily relies on annotated data. However, manual data annotation is costly and demands substantial human effort. In order to address this challenge, we propose a framework that can automatically annotate gesture classes and identify their temporal ranges. Our framework consists of two key components: (1) a novel annotation model that leverages the Connectionist Temporal Classification (CTC) loss, and (2) a semi-supervised learning pipeline that enables the model to improve its performance by training on its own predictions, known as pseudo labels. These high-quality pseudo labels can also be used to enhance the accuracy of other downstream gesture recognition models. To evaluate our framework, we conducted experiments using two publicly available gesture datasets. Our ablation study demonstrates that our annotation model design surpasses the baseline in terms of both gesture classification accuracy (3-4% improvement) and localization accuracy (71-75% improvement). Additionally, we illustrate that the pseudo-labeled dataset produced from the proposed framework significantly boosts the accuracy of a pre-trained downstream gesture recognition model by 11-18%. We believe that this annotation framework has immense potential to improve the training of downstream gesture recognition models using unlabeled datasets.

Junxiao Shen, Matthias De Lange, Xuhai "Orson" Xu et al.

Providing users with accurate gestural interfaces, such as gesture recognition based on wrist-worn devices, is a key challenge in mixed reality. However, static machine learning processes in gesture recognition assume that training and test data come from the same underlying distribution. Unfortunately, in real-world applications involving gesture recognition, such as gesture recognition based on wrist-worn devices, the data distribution may change over time. We formulate this problem of adapting recognition models to new tasks, where new data patterns emerge, as open-world gesture recognition (OWGR). We propose the use of continual learning to enable machine learning models to be adaptive to new tasks without degrading performance on previously learned tasks. However, the process of exploring parameters for questions around when, and how, to train and deploy recognition models requires resource-intensive user studies may be impractical. To address this challenge, we propose a design engineering approach that enables offline analysis on a collected large-scale dataset by systematically examining various parameters and comparing different continual learning methods. Finally, we provide design guidelines to enhance the development of an open-world wrist-worn gesture recognition process.

Hang Ren, Aivar Sootla, Taher Jafferjee et al.

We consider a context-dependent Reinforcement Learning (RL) setting, which is characterized by: a) an unknown finite number of not directly observable contexts; b) abrupt (discontinuous) context changes occurring during an episode; and c) Markovian context evolution. We argue that this challenging case is often met in applications and we tackle it using a Bayesian approach and variational inference. We adapt a sticky Hierarchical Dirichlet Process (HDP) prior for model learning, which is arguably best-suited for Markov process modeling. We then derive a context distillation procedure, which identifies and removes spurious contexts in an unsupervised fashion. We argue that the combination of these two components allows to infer the number of contexts from data thus dealing with the context cardinality assumption. We then find the representation of the optimal policy enabling efficient policy learning using off-the-shelf RL algorithms. Finally, we demonstrate empirically (using gym environments cart-pole swing-up, drone, intersection) that our approach succeeds where state-of-the-art methods of other frameworks fail and elaborate on the reasons for such failures.

Junxiao Shen, John Dudley, Per Ola Kristensson

Deep learning approaches deliver state-of-the-art performance in recognition of spatiotemporal human motion data. However, one of the main challenges in these recognition tasks is limited available training data. Insufficient training data results in over-fitting and data augmentation is one approach to address this challenge. Existing data augmentation strategies based on scaling, shifting and interpolating offer limited generalizability and typically require detailed inspection of the dataset as well as hundreds of GPU hours for hyperparameter optimization. In this paper, we present a novel automatic data augmentation model, the Imaginative Generative Adversarial Network (GAN), that approximates the distribution of the input data and samples new data from this distribution. It is automatic in that it requires no data inspection and little hyperparameter tuning and therefore it is a low-cost and low-effort approach to generate synthetic data. We demonstrate our approach on small-scale skeleton-based datasets with a comprehensive experimental analysis. Our results show that the augmentation strategy is fast to train and can improve classification accuracy for both conventional neural networks and state-of-the-art methods.