Tiantian Geng

Tiantian Geng, Teng Wang, Jinming Duan et al.

Existing audio-visual event localization (AVE) handles manually trimmed videos with only a single instance in each of them. However, this setting is unrealistic as natural videos often contain numerous audio-visual events with different categories. To better adapt to real-life applications, in this paper we focus on the task of dense-localizing audio-visual events, which aims to jointly localize and recognize all audio-visual events occurring in an untrimmed video. The problem is challenging as it requires fine-grained audio-visual scene and context understanding. To tackle this problem, we introduce the first Untrimmed Audio-Visual (UnAV-100) dataset, which contains 10K untrimmed videos with over 30K audio-visual events. Each video has 2.8 audio-visual events on average, and the events are usually related to each other and might co-occur as in real-life scenes. Next, we formulate the task using a new learning-based framework, which is capable of fully integrating audio and visual modalities to localize audio-visual events with various lengths and capture dependencies between them in a single pass. Extensive experiments demonstrate the effectiveness of our method as well as the significance of multi-scale cross-modal perception and dependency modeling for this task.

Jingfei Xia, Mingchen Zhuge, Tiantian Geng et al.

Figure skating scoring is challenging because it requires judging the technical moves of the players as well as their coordination with the background music. Most learning-based methods cannot solve it well for two reasons: 1) each move in figure skating changes quickly, hence simply applying traditional frame sampling will lose a lot of valuable information, especially in 3 to 5 minutes long videos; 2) prior methods rarely considered the critical audio-visual relationship in their models. Due to these reasons, we introduce a novel architecture, named Skating-Mixer. It extends the MLP framework into a multimodal fashion and effectively learns long-term representations through our designed memory recurrent unit (MRU). Aside from the model, we collected a high-quality audio-visual FS1000 dataset, which contains over 1000 videos on 8 types of programs with 7 different rating metrics, overtaking other datasets in both quantity and diversity. Experiments show the proposed method achieves SOTAs over all major metrics on the public Fis-V and our FS1000 dataset. In addition, we include an analysis applying our method to the recent competitions in Beijing 2022 Winter Olympic Games, proving our method has strong applicability.

Cui Yakun, Xingqun Qi, TianTian Geng et al.

Recent advances in Vision-Language Models (VLMs) have substantially enhanced their ability across multimodal video understanding benchmarks spanning temporal, action, object, and spatial understanding. However, we identify a critical yet overlooked issue: when embedded on-screen text contradicts the visual scene, existing VLMs systematically hallucinate, prioritizing overlay textual semantics over the actual visual content. We define this phenomenon as Text Overlay-Induced Hallucination (TOIH). In this work, we propose VisualTextTrap, the first comprehensive benchmark, including large-scale human-validated samples with specifically designed evaluation metrics. In particular, we construct VisualTextTrap from widely-used public datasets using a scalable hybrid pipeline of VLMs assisted text generation and rigorous manual verification. The benchmark features 6,057 samples annotated across 88 fine-grained attributes within four dimensions, with hallucination intensity quantified on a five-level scale (L1--L5) that reflects the semantic contradiction between overlay text and visual reality. Moreover, we propose Visual Text Hallucination Mitigation Mixture-of-Experts (VTHM-MoE), a novel Vision-Text Disentanglement framework that employs a dual-encoder architecture. Concretely, four dimension-specialized expert modules spanning Temporal, Action, Object, and Spatial reasoning are first pre-trained to identify and leverage cross-modal discrepancies between textual semantics and actual video content. We develop an Adaptive Token Routing Strategy to enable dynamic expert allocation, conferring robust resistance to TOIH while preserving performance on uncontaminated videos. Extensive experiments conducted on our VisualTextTrap benchmark verify the effectiveness of VTHM-MoE, outperforming state-of-the-art counterparts with diverse video question answering tasks.

Xiangchen Wang, Weiye Zhu, Teng Wang et al.

Recent navigation systems achieve strong benchmark results, yet real-world deployment often remains visibly stop-and-go. This bottleneck arises because the sense-inference-execution loop is still blocking: after each new observation, the controller must wait for sensing, transmission, and inference before motion can continue. Reducing action-generation cost alone therefore does not remove redundant waiting. To address this issue, we present LiveVLN, a training-free framework for more continuous embodied navigation by augmenting pretrained VLM navigators with multi-step action continuation. Instead of pausing for each full sense-and-inference round, LiveVLN overlaps execution with the processing of newly arrived observations, allowing refreshed future actions to be handed off before the current executable prefix is exhausted. This design keeps actions continuously available during motion, reducing idle waiting and enabling smoother online execution. The framework operates at runtime and can be integrated with compatible pretrained VLM navigators. Across R2R and RxR, LiveVLN preserves benchmark performance while reducing waiting time and improving action availability. In real-world deployments, it cuts average episode waiting time by up to $77.7\%$ and shortens wall-clock episode time by $12.6\%$ on StreamVLN and $19.6\%$ on NaVIDA, yielding more coherent execution during deployment. Code is available at https://github.com/NIneeeeeem/LiveVLN.

Nannan Zhu, Yonghao Dong, Teng Wang et al.

While multimodal large language models (MLLMs) exhibit strong performance on single-video tasks (e.g., video question answering), their ability across multiple videos remains critically underexplored. However, this capability is essential for real-world applications, including multi-camera surveillance and cross-video procedural learning. To bridge this gap, we present CVBench, the first comprehensive benchmark designed to assess cross-video relational reasoning rigorously. CVBench comprises 1,000 question-answer pairs spanning three hierarchical tiers: cross-video object association (identifying shared entities), cross-video event association (linking temporal or causal event chains), and cross-video complex reasoning (integrating commonsense and domain knowledge). Built from five domain-diverse video clusters (e.g., sports, life records), the benchmark challenges models to synthesise information across dynamic visual contexts. Extensive evaluation of 10+ leading MLLMs (including GPT-4o, Gemini-2.0-flash, Qwen2.5-VL) under zero-shot or chain-of-thought prompting paradigms. Key findings reveal stark performance gaps: even top models, such as GPT-4o, achieve only 60% accuracy on causal reasoning tasks, compared to the 91% accuracy of human performance. Crucially, our analysis reveals fundamental bottlenecks inherent in current MLLM architectures, notably deficient inter-video context retention and poor disambiguation of overlapping entities. CVBench establishes a rigorous framework for diagnosing and advancing multi-video reasoning, offering architectural insights for next-generation MLLMs. The data and evaluation code are available at https://github.com/Hokhim2/CVBench.

Weiye Zhu, Zekai Zhang, Xiangchen Wang et al.

Vision-and-Language Navigation (VLN) requires agents to interpret natural language instructions and act coherently in visually rich environments. However, most existing methods rely on reactive state-action mappings without explicitly modeling how actions causally transform subsequent visual observations. Lacking such vision-action causality, agents cannot anticipate the visual changes induced by its own actions, leading to unstable behaviors, weak generalization, and cumulative error along trajectory. To address these issues, we introduce \textsc{NaVIDA} (\textbf{Nav}igation with \textbf{I}nverse \textbf{D}ynamics \textbf{A}ugmentation), a unified VLN framework that couples policy learning with action-grounded visual dynamics and adaptive execution. \textsc{NaVIDA} augments training with chunk-based inverse-dynamics supervision to learn causal relationship between visual changes and corresponding actions. To structure this supervision and extend the effective planning range, \textsc{NaVIDA} employs hierarchical probabilistic action chunking (HPAC), which organizes trajectories into multi-step chunks and provides discriminative, longer-range visual-change cues. To further curb error accumulation and stabilize behavior at inference, an entropy-guided mechanism adaptively sets the execution horizon of action chunks. Extensive experiments show that \textsc{NaVIDA} achieves superior navigation performance compared to state-of-the-art methods with fewer parameters (3B vs. 8B). Real-world robot evaluations further validate the practical feasibility and effectiveness of our approach. Code and data will be available upon acceptance.

Tiantian Geng, Jinrui Zhang, Qingni Wang et al.

Despite impressive advancements in video understanding, most efforts remain limited to coarse-grained or visual-only video tasks. However, real-world videos encompass omni-modal information (vision, audio, and speech) with a series of events forming a cohesive storyline. The lack of multi-modal video data with fine-grained event annotations and the high cost of manual labeling are major obstacles to comprehensive omni-modality video perception. To address this gap, we propose an automatic pipeline consisting of high-quality multi-modal video filtering, semantically coherent omni-modal event boundary detection, and cross-modal correlation-aware event captioning. In this way, we present LongVALE, the first-ever Vision-Audio-Language Event understanding benchmark comprising 105K omni-modal events with precise temporal boundaries and detailed relation-aware captions within 8.4K high-quality long videos. Further, we build a baseline that leverages LongVALE to enable video large language models (LLMs) for omni-modality fine-grained temporal video understanding for the first time. Extensive experiments demonstrate the effectiveness and great potential of LongVALE in advancing comprehensive multi-modal video understanding.

Tiantian Geng, Teng Wang, Jinming Duan et al.

Video event localization tasks include temporal action localization (TAL), sound event detection (SED) and audio-visual event localization (AVEL). Existing methods tend to over-specialize on individual tasks, neglecting the equal importance of these different events for a complete understanding of video content. In this work, we aim to develop a unified framework to solve TAL, SED and AVEL tasks together to facilitate holistic video understanding. However, it is challenging since different tasks emphasize distinct event characteristics and there are substantial disparities in existing task-specific datasets (size/domain/duration). It leads to unsatisfactory results when applying a naive multi-task strategy. To tackle the problem, we introduce UniAV, a Unified Audio-Visual perception network to effectively learn and share mutually beneficial knowledge across tasks and modalities. Concretely, we propose a unified audio-visual encoder to derive generic representations from multiple temporal scales for videos from all tasks. Meanwhile, task-specific experts are designed to capture the unique knowledge specific to each task. Besides, instead of using separate prediction heads, we develop a novel unified language-aware classifier by utilizing semantic-aligned task prompts, enabling our model to flexibly localize various instances across tasks with an impressive open-set ability to localize novel categories. Extensive experiments demonstrate that UniAV, with its unified architecture, significantly outperforms both single-task models and the naive multi-task baseline across all three tasks. It achieves superior or on-par performances compared to the state-of-the-art task-specific methods on ActivityNet 1.3, DESED and UnAV-100 benchmarks.

Lu Zhu, Tiantian Geng, Yangye Chen et al.

Recently, rapid advancements have been made in multimodal large language models (MLLMs), especially in video understanding tasks. However, current research focuses on simple video scenarios, failing to reflect the complex and diverse nature of real-world audio-visual events in videos. To bridge this gap, we firstly introduce R-AVST, a dataset for audio-visual reasoning featuring fine-grained spatio-temporal annotations. In constructing this, we design a pipeline consisting of LLM-based key object extraction, automatic spatial annotation and manual quality inspection, resulting in over 5K untrimmed videos with 27K objects across 100 types of audio-visual events. Building on this dataset, we define three core tasks for spatio-temporal reasoning in audio-visual scenes and generate more than 8K high-quality, evenly distributed question-answer pairs to effectively benchmark model performance. To further enhance reasoning, we propose AVST-Zero, a reinforcement learning-based model that avoids intermediate supervision, directly optimizing behavior via carefully designed multi-dimensional rewards. Extensive experiments validate the effectiveness of our R-AVST in advancing audio-visual spatio-temporal reasoning, upon which AVST-Zero demonstrates competitive performance compared to existing models. To the best of our knowledge, R-AVST is the first dataset designed for real-world audio-visual spatio-temporal reasoning, and AVST-Zero offers a novel perspective for tackling future challenges in this domain.

Yuting Zhang, Tiantian Geng, Luoying Hao et al.

Contemporary cardiovascular management involves complex consideration and integration of multimodal cardiac datasets, where each modality provides distinct but complementary physiological characteristics. While the effective integration of multiple modalities could yield a holistic clinical profile that accurately models the true clinical situation with respect to data modalities and their relatives weightings, current methodologies remain limited by: 1) the scarcity of patient- and time-aligned multimodal data; 2) reliance on isolated single-modality or rigid multimodal input combinations; 3) alignment strategies that prioritize cross-modal similarity over complementarity; and 4) a narrow single-task focus. In response to these limitations, a comprehensive multimodal dataset was curated for immediate application, integrating laboratory test results, electrocardiograms, and echocardiograms with clinical outcomes. Subsequently, a unified framework, Textual Guidance Multimodal fusion for Multiple cardiac tasks (TGMM), was proposed. TGMM incorporated three key components: 1) a MedFlexFusion module designed to capture the unique and complementary characteristics of medical modalities and dynamically integrate data from diverse cardiac sources and their combinations; 2) a textual guidance module to derive task-relevant representations tailored to diverse clinical objectives, including heart disease diagnosis, risk stratification and information retrieval; and 3) a response module to produce final decisions for all these tasks. Furthermore, this study systematically explored key features across multiple modalities and elucidated their synergistic contributions in clinical decision-making. Extensive experiments showed that TGMM outperformed state-of-the-art methods across multiple clinical tasks, with additional validation confirming its robustness on another public dataset.