Prolonged Exposure (PE) therapy is an effective treatment for post-traumatic stress disorder (PTSD), but evaluating therapist fidelity remains labor-intensive due to the need for manual review of session recordings. We present a method for the automatic temporal localization of key PE fidelity elements -- identifying their start and stop times -- directly from session audio and transcripts. Our approach fine-tunes a large pre-trained audio-language model, Qwen2-Audio, using Low-Rank Adaptation (LoRA) to process focused 30-second windows of audio-transcript input. Fidelity labels for three core protocol phases -- therapist orientation (P1), imaginal exposure (P2), and post-imaginal processing (P3) -- are generated via LLM-based prompting and verified by trained raters. The model is trained to predict normalized boundary offsets using soft supervision guided by task-specific prompts. On a dataset of 313 real PE sessions, our best configuration (LoRA rank 8, 30s windows) achieves a mean absolute error (MAE) of 5.3 seconds across tasks. We further analyze the effects of window size and LoRA rank, highlighting the importance of context granularity and model adaptation. This work introduces a scalable framework for fidelity tracking in PE therapy, with potential to support clinician training, supervision, and quality assurance.
In recent years, numerous tasks have been proposed to encourage model to develop specified capability in understanding audio-visual scene, primarily categorized into temporal localization, spatial localization, spatio-temporal reasoning, and pixel-level understanding. Instead, human possesses a unified understanding ability for diversified tasks. Therefore, designing an audio-visual model with general capability to unify these tasks is of great value. However, simply joint training for all tasks can lead to interference due to the heterogeneity of audiovisual data and complex relationship among tasks. We argue that this problem can be solved through explicit cooperation among tasks. To achieve this goal, we propose a unified learning method which achieves explicit inter-task cooperation from both the perspectives of data and model thoroughly. Specifically, considering the labels of existing datasets are simple words, we carefully refine these datasets and construct an Audio-Visual Unified Instruction-tuning dataset with Explicit reasoning process (AV-UIE), which clarifies the cooperative relationship among tasks. Subsequently, to facilitate concrete cooperation in learning stage, an interaction-aware LoRA structure with multiple LoRA heads is designed to learn different aspects of audiovisual data interaction. By unifying the explicit cooperation across the data and model aspect, our method not only surpasses existing unified audio-visual model on multiple tasks, but also outperforms most specialized models for certain tasks. Furthermore, we also visualize the process of explicit cooperation and surprisingly find that each LoRA head has certain audio-visual understanding ability. Code and dataset: https://github.com/GeWu-Lab/Crab
Spatio-temporal localization is vital for precise interactions across diverse domains, from biological research to autonomous navigation and interactive interfaces. Current video-based approaches, while proficient in tracking, lack the sophisticated reasoning capabilities of large language models, limiting their contextual understanding and generalization. We introduce VideoMolmo, a large multimodal model tailored for fine-grained spatio-temporal pointing conditioned on textual descriptions. Building upon the Molmo architecture, VideoMolmo incorporates a temporal module utilizing an attention mechanism to condition each frame on preceding frames, ensuring temporal consistency. Additionally, our novel temporal mask fusion pipeline employs SAM2 for bidirectional point propagation, significantly enhancing coherence across video sequences. This two-step decomposition, i.e., first using the LLM to generate precise pointing coordinates, then relying on a sequential mask-fusion module to produce coherent segmentation, not only simplifies the task for the language model but also enhances interpretability. Due to the lack of suitable datasets, we curate a comprehensive dataset comprising 72k video-caption pairs annotated with 100k object points. To evaluate the generalization of VideoMolmo, we introduce VPoS-Bench, a challenging out-of-distribution benchmark spanning five real-world scenarios: Cell Tracking, Egocentric Vision, Autonomous Driving, Video-GUI Interaction, and Robotics. We also evaluate our model on Referring Video Object Segmentation (Refer-VOS) and Reasoning VOS tasks. In comparison to existing models, VideoMolmo substantially improves spatio-temporal pointing accuracy and reasoning capability. Our code and models are publicly available at https://github.com/mbzuai-oryx/VideoMolmo.
Despite advances in general video understanding, Video Large Language Models (Video-LLMs) face challenges in precise temporal localization due to discrete time representations and limited temporally aware datasets. Existing methods for temporal expression either conflate time with text-based numerical values, add a series of dedicated temporal tokens, or regress time using specialized temporal grounding heads. To address these issues, we introduce DisTime, a lightweight framework designed to enhance temporal comprehension in Video-LLMs. DisTime employs a learnable token to create a continuous temporal embedding space and incorporates a Distribution-based Time Decoder that generates temporal probability distributions, effectively mitigating boundary ambiguities and maintaining temporal continuity. Additionally, the Distribution-based Time Encoder re-encodes timestamps to provide time markers for Video-LLMs. To overcome temporal granularity limitations in existing datasets, we propose an automated annotation paradigm that combines the captioning capabilities of Video-LLMs with the localization expertise of dedicated temporal models. This leads to the creation of InternVid-TG, a substantial dataset with 1.25M temporally grounded events across 179k videos, surpassing ActivityNet-Caption by 55 times. Extensive experiments demonstrate that DisTime achieves state-of-the-art performance across benchmarks in three time-sensitive tasks while maintaining competitive performance in Video QA tasks. Code and data are released at https://github.com/josephzpng/DisTime.
Daily Activity Recordings for Artificial Intelligence (DARai, pronounced "Dahr-ree") is a multimodal, hierarchically annotated dataset constructed to understand human activities in real-world settings. DARai consists of continuous scripted and unscripted recordings of 50 participants in 10 different environments, totaling over 200 hours of data from 20 sensors including multiple camera views, depth and radar sensors, wearable inertial measurement units (IMUs), electromyography (EMG), insole pressure sensors, biomonitor sensors, and gaze tracker. To capture the complexity in human activities, DARai is annotated at three levels of hierarchy: (i) high-level activities (L1) that are independent tasks, (ii) lower-level actions (L2) that are patterns shared between activities, and (iii) fine-grained procedures (L3) that detail the exact execution steps for actions. The dataset annotations and recordings are designed so that 22.7% of L2 actions are shared between L1 activities and 14.2% of L3 procedures are shared between L2 actions. The overlap and unscripted nature of DARai allows counterfactual activities in the dataset. Experiments with various machine learning models showcase the value of DARai in uncovering important challenges in human-centered applications. Specifically, we conduct unimodal and multimodal sensor fusion experiments for recognition, temporal localization, and future action anticipation across all hierarchical annotation levels. To highlight the limitations of individual sensors, we also conduct domain-variant experiments that are enabled by DARai's multi-sensor and counterfactual activity design setup. The code, documentation, and dataset are available at the dedicated DARai website: https://alregib.ece.gatech.edu/software-and-datasets/darai-daily-activity-recordings-for-artificial-intelligence-and-machine-learning/
Soccer is a globally popular sporting event, typically characterized by long matches and distinctive highlight moments. Recent advances in Multimodal Large Language Models (MLLMs) offer promising capabilities in temporal grounding and video understanding, soccer commentary generation often requires precise temporal localization and semantically rich descriptions over long-form video. However, existing soccer MLLMs often rely on the temporal a priori for caption generation, so they cannot process the soccer video end-to-end. While some traditional approaches follow a two-step paradigm that is complex and fails to capture the global context to achieve suboptimal performance. To solve the above issues, we present TimeSoccer, the first end-to-end soccer MLLM for Single-anchor Dense Video Captioning (SDVC) in full-match soccer videos. TimeSoccer jointly predicts timestamps and generates captions in a single pass, enabling global context modeling across 45-minute matches. To support long video understanding of soccer matches, we introduce MoFA-Select, a training-free, motion-aware frame compression module that adaptively selects representative frames via a coarse-to-fine strategy, and incorporates complementary training paradigms to strengthen the model's ability to handle long temporal sequences. Extensive experiments demonstrate that our TimeSoccer achieves State-of-The-Art (SoTA) performance on the SDVC task in an end-to-end form, generating high-quality commentary with accurate temporal alignment and strong semantic relevance.
Multimodal LLMs are turning their focus to video benchmarks, however most video benchmarks only provide outcome supervision, with no intermediate or interpretable reasoning steps. This makes it challenging to assess if models are truly able to combine perceptual and temporal information to reason about videos, or simply get the correct answer by chance or by exploiting linguistic biases. To remedy this, we provide a new video reasoning dataset called MINERVA for modern multimodal models. Each question in the dataset comes with 5 answer choices, as well as detailed, hand-crafted reasoning traces. Our dataset is multimodal, diverse in terms of video domain and length, and consists of complex multi-step questions. Extensive benchmarking shows that our dataset provides a challenge for frontier open-source and proprietary models. We perform fine-grained error analysis to identify common failure modes across various models, and create a taxonomy of reasoning errors. We use this to explore both human and LLM-as-a-judge methods for scoring video reasoning traces, and find that failure modes are primarily related to temporal localization, followed by visual perception errors, as opposed to logical or completeness errors. The dataset, along with questions, answer candidates and reasoning traces will be publicly available under https://github.com/google-deepmind/neptune?tab=readme-ov-file\#minerva.
Face detection and face recognition have been in the focus of vision community since the very beginnings. Inspired by the success of the original Videoface digitizer, a pioneering device that allowed users to capture video signals from any source, we have designed an advanced video analytics tool to efficiently create structured video stories, i.e. identity-based information catalogs. VideoFace2.0 is the name of the developed system for spatial and temporal localization of each unique face in the input video, i.e. face re-identification (ReID), which also allows their cataloging, characterization and creation of structured video outputs for later downstream tasks. Developed near real-time solution is primarily designed to be utilized in application scenarios involving TV production, media analysis, and as an efficient tool for creating large video datasets necessary for training machine learning (ML) models in challenging vision tasks such as lip reading and multimodal speech recognition. Conducted experiments confirm applicability of the proposed face ReID algorithm that is combining the concepts of face detection, face recognition and passive tracking-by-detection in order to achieve robust and efficient face ReID. The system is envisioned as a compact and modular extensions of the existing video production equipment. Presented results are based on test implementation that achieves between 18-25 fps on consumer type notebook. Ablation experiments also confirmed that the proposed algorithm brings relative gain in the reduction of number of false identities in the range of 73%-93%. We hope that the presented work and shared code implementation will stimulate further interest in development of similar, application specific video analysis tools, and lower the entry barrier for production of high-quality multi-modal datasets in the future.
Timing of clinical events is central to characterization of patient trajectories, enabling analyses such as process tracing, forecasting, and causal reasoning. However, structured electronic health records capture few data elements critical to these tasks, while clinical reports lack temporal localization of events in structured form. We present a system that transforms case reports into textual time series-structured pairs of textual events and timestamps. We contrast manual and large language model (LLM) annotations (n=320 and n=390 respectively) of ten randomly-sampled PubMed open-access (PMOA) case reports (N=152,974) and assess inter-LLM agreement (n=3,103; N=93). We find that the LLM models have moderate event recall(O1-preview: 0.80) but high temporal concordance among identified events (O1-preview: 0.95). By establishing the task, annotation, and assessment systems, and by demonstrating high concordance, this work may serve as a benchmark for leveraging the PMOA corpus for temporal analytics.
Traffic crash detection in long-form surveillance videos is critical for emergency response and infrastructure planning but remains difficult due to the brief and rare nature of crash events. We introduce HybridMamba, a novel architecture that combines visual transformers with state-space temporal modeling to achieve accurate crash time localization. Our method uses multi-level token compression and hierarchical temporal processing to remain computationally efficient without sacrificing temporal resolution. Evaluated on a large-scale dataset from the Iowa Department of Transportation, HybridMamba achieves a mean absolute error of 1.50 seconds, with 65.2 percent of predictions within one second of the ground truth. It outperforms recent video-language models such as TimeChat and VideoLLaMA2 by up to 2.8 seconds, while using significantly fewer parameters. Our results demonstrate strong generalization across videos ranging from 2 to 40 minutes in diverse conditions. HybridMamba offers a robust and efficient solution for fine-grained temporal localization in traffic surveillance. The code will be released upon publication.
Previous research in human gesture recognition has largely overlooked multi-person interactions, which are crucial for understanding the social context of naturally occurring gestures. This limitation in existing datasets presents a significant challenge in aligning human gestures with other modalities like language and speech. To address this issue, we introduce SocialGesture, the first large-scale dataset specifically designed for multi-person gesture analysis. SocialGesture features a diverse range of natural scenarios and supports multiple gesture analysis tasks, including video-based recognition and temporal localization, providing a valuable resource for advancing the study of gesture during complex social interactions. Furthermore, we propose a novel visual question answering (VQA) task to benchmark vision language models'(VLMs) performance on social gesture understanding. Our findings highlight several limitations of current gesture recognition models, offering insights into future directions for improvement in this field. SocialGesture is available at huggingface.co/datasets/IrohXu/SocialGesture.
Traffic Atomic Activity which describes traffic patterns for topological intersection dynamics is a crucial topic for the advancement of intelligent driving systems. However, existing atomic activity datasets are collected from an egocentric view, which cannot support the scenarios where traffic activities in an entire intersection are required. Moreover, existing datasets only provide video-level atomic activity annotations, which require exhausting efforts to manually trim the videos for recognition and limit their applications to untrimmed videos. To bridge this gap, we introduce the Aerial Traffic Atomic Activity Recognition and Segmentation (ATARS) dataset, the first aerial dataset designed for multi-label atomic activity analysis. We offer atomic activity labels for each frame, which accurately record the intervals for traffic activities. Moreover, we propose a novel task, Multi-label Temporal Atomic Activity Recognition, enabling the study of accurate temporal localization for atomic activity and easing the burden of manual video trimming for recognition. We conduct extensive experiments to evaluate existing state-of-the-art models on both atomic activity recognition and temporal atomic activity segmentation. The results highlight the unique challenges of our ATARS dataset, such as recognizing extremely small objects' activities. We further provide comprehensive discussion analyzing these challenges and offer valuable insights for future direction to improve recognizing atomic activity in aerial view. Our source code and dataset are available at https://github.com/magecliff96/ATARS/
Videos, with their unique temporal dimension, demand precise grounded understanding, where answers are directly linked to visual, interpretable evidence. Despite significant breakthroughs in reasoning capabilities within Large Language Models, multi-modal reasoning - especially for videos - remains unexplored. In this work, we introduce VideoMind, a novel video-language agent designed for temporal-grounded video understanding. VideoMind incorporates two key innovations: (i) We identify essential capabilities for video temporal reasoning and develop a role-based agentic workflow, including a planner for coordinating different roles, a grounder for temporal localization, a verifier to assess temporal interval accuracy, and an answerer for question-answering. (ii) To efficiently integrate these diverse roles, we propose a novel Chain-of-LoRA strategy, enabling seamless role-switching via lightweight LoRA adaptors while avoiding the overhead of multiple models, thus balancing efficiency and flexibility. Extensive experiments on 14 public benchmarks, including 3 on grounded video question-answering (Grounded VideoQA), 6 on video temporal grounding (VTG), and 5 on general video question-answering (VideoQA), verify that our agent achieves state-of-the-art performance on diverse video understanding tasks, underscoring its effectiveness in advancing video agent and long-form temporal reasoning.
In the domain of audio-visual event perception, which focuses on the temporal localization and classification of events across distinct modalities (audio and visual), existing approaches are constrained by the vocabulary available in their training data. This limitation significantly impedes their capacity to generalize to novel, unseen event categories. Furthermore, the annotation process for this task is labor-intensive, requiring extensive manual labeling across modalities and temporal segments, limiting the scalability of current methods. Current state-of-the-art models ignore the shifts in event distributions over time, reducing their ability to adjust to changing video dynamics. Additionally, previous methods rely on late fusion to combine audio and visual information. While straightforward, this approach results in a significant loss of multimodal interactions. To address these challenges, we propose Audio-Visual Adaptive Video Analysis ($\text{AV}^2\text{A}$), a model-agnostic approach that requires no further training and integrates a score-level fusion technique to retain richer multimodal interactions. $\text{AV}^2\text{A}$ also includes a within-video label shift algorithm, leveraging input video data and predictions from prior frames to dynamically adjust event distributions for subsequent frames. Moreover, we present the first training-free, open-vocabulary baseline for audio-visual event perception, demonstrating that $\text{AV}^2\text{A}$ achieves substantial improvements over naive training-free baselines. We demonstrate the effectiveness of $\text{AV}^2\text{A}$ on both zero-shot and weakly-supervised state-of-the-art methods, achieving notable improvements in performance metrics over existing approaches.
Automated surgical workflow analysis is crucial for education, research, and clinical decision-making, but the lack of annotated datasets hinders the development of accurate and comprehensive workflow analysis solutions. We introduce a novel approach for addressing the sparsity and heterogeneity of annotated training data inspired by the human learning procedure of watching experts and understanding their explanations. Our method leverages a video-language model trained on alignment, denoising, and generative tasks to learn short-term spatio-temporal and multimodal representations. A task-specific temporal model is then used to capture relationships across entire videos. To achieve comprehensive video-language understanding in the surgical domain, we introduce a data collection and filtering strategy to construct a large-scale pretraining dataset from educational YouTube videos. We then utilize parameter-efficient fine-tuning by projecting downstream task annotations from publicly available surgical datasets into the language domain. Extensive experiments in two surgical domains demonstrate the effectiveness of our approach, with performance improvements of up to 7% in phase segmentation tasks, 8% in zero-shot phase segmentation, and comparable capabilities to fully-supervised models in few-shot settings. Harnessing our model's capabilities for long-range temporal localization and text generation, we present the first comprehensive solution for dense video captioning (DVC) of surgical videos, addressing this task despite the absence of existing DVC datasets in the surgical domain. We introduce a novel approach to surgical workflow understanding that leverages video-language pretraining, large-scale video pretraining, and optimized fine-tuning. Our method improves performance over state-of-the-art techniques and enables new downstream tasks for surgical video understanding.
Localizing user-queried events through natural language is crucial for video understanding models. Recent methods predominantly adapt Video LLMs to generate event boundary timestamps to handle temporal localization tasks, which struggle to leverage LLMs' powerful semantic understanding. In this work, we introduce MeCo, a novel timestamp-free framework that enables video LLMs to fully harness their intrinsic semantic capabilities for temporal localization tasks. Rather than outputting boundary timestamps, MeCo partitions videos into holistic event and transition segments based on the proposed structural token generation and grounding pipeline, derived from video LLMs' temporal structure understanding capability. We further propose a query-focused captioning task that compels the LLM to extract fine-grained, event-specific details, bridging the gap between localization and higher-level semantics and enhancing localization performance. Extensive experiments on diverse temporal localization tasks show that MeCo consistently outperforms boundary-centric methods, underscoring the benefits of a semantic-driven approach for temporal localization with video LLMs.
In the rapidly evolving domain of video understanding, Video Question Answering (VideoQA) remains a focal point. However, existing datasets exhibit gaps in temporal and spatial granularity, which consequently limits the capabilities of existing VideoQA methods. This paper introduces the Multi-Object Multi-Actor Question Answering (MOMA-QA) dataset, which is designed to address these shortcomings by emphasizing temporal localization, spatial relationship reasoning, and entity-centric queries. With ground truth scene graphs and temporal interval annotations, MOMA-QA is ideal for developing models for fine-grained video understanding. Furthermore, we present a novel video-language model, SGVLM, which incorporates a scene graph predictor, an efficient frame retriever, and a pre-trained large language model for temporal localization and fine-grained relationship understanding. Evaluations on MOMA-QA and other public datasets demonstrate the superior performance of our model, setting new benchmarks for VideoQA.
Temporal localization in untrimmed videos, which aims to identify specific timestamps, is crucial for video understanding but remains challenging. This task encompasses several subtasks, including temporal action localization, temporal video grounding, moment retrieval, and generic event boundary detection. Existing methods in each subfield are typically designed for specific tasks and lack generalizability across domains. In this paper, we propose TimeLoc, a unified end-to-end framework for timestamp localization that can handle multiple tasks. First, our approach employs a simple yet effective one-stage localization model that supports text queries as input and multiple actions as output. Second, we jointly train the video encoder and localization model in an end-to-end manner. To efficiently process long videos, we introduce temporal chunking, enabling the handling of videos with over 30k frames. Third, we find that fine-tuning pre-trained text encoders with a multi-stage training strategy further enhances text-conditioned localization. TimeLoc achieves state-of-the-art results across multiple benchmarks: +1.3% and +1.9% mAP over previous best methods on THUMOS14 and EPIC-Kitchens-100, +1.1% on Kinetics-GEBD, +2.94% mAP on QVHighlights, and significant improvements in temporal video grounding (+11.5% on TACoS and +6.7% on Charades-STA under [email omitted]). Our code and checkpoints will be released at https://github.com/sming256/TimeLoc.
Marine ecosystem monitoring via Passive Acoustic Monitoring (PAM) generates vast data, but deep learning often requires precise annotations and short segments. We introduce DSMIL-LocNet, a Multiple Instance Learning framework for whale call detection and localization using only bag-level labels. Our dual-stream model processes 2-30 minute audio segments, leveraging spectral and temporal features with attention-based instance selection. Tests on Antarctic whale data show longer contexts improve classification (F1: 0.8-0.9) while medium instances ensure localization precision (0.65-0.70). This suggests MIL can enhance scalable marine monitoring. Code: https://github.com/Ragib-Amin-Nihal/DSMIL-Loc
Transformer has attracted increasing interest in STVG, owing to its end-to-end pipeline and promising result. Existing Transformer-based STVG approaches often leverage a set of object queries, which are initialized simply using zeros and then gradually learn target position information via iterative interactions with multimodal features, for spatial and temporal localization. Despite simplicity, these zero object queries, due to lacking target-specific cues, are hard to learn discriminative target information from interactions with multimodal features in complicated scenarios (\e.g., with distractors or occlusion), resulting in degradation. Addressing this, we introduce a novel Target-Aware Transformer for STVG (TA-STVG), which seeks to adaptively generate object queries via exploring target-specific cues from the given video-text pair, for improving STVG. The key lies in two simple yet effective modules, comprising text-guided temporal sampling (TTS) and attribute-aware spatial activation (ASA), working in a cascade. The former focuses on selecting target-relevant temporal cues from a video utilizing holistic text information, while the latter aims at further exploiting the fine-grained visual attribute information of the object from previous target-aware temporal cues, which is applied for object query initialization. Compared to existing methods leveraging zero-initialized queries, object queries in our TA-STVG, directly generated from a given video-text pair, naturally carry target-specific cues, making them adaptive and better interact with multimodal features for learning more discriminative information to improve STVG. In our experiments on three benchmarks, TA-STVG achieves state-of-the-art performance and significantly outperforms the baseline, validating its efficacy.