Video Large Language Models (Video-LLMs) have demonstrated remarkable capabilities in coarse-grained video understanding, however, they struggle with fine-grained temporal grounding. In this paper, we introduce Grounded-VideoLLM, a novel Video-LLM adept at perceiving and reasoning over specific video moments in a fine-grained manner. We identify that current Video-LLMs have limitations for fine-grained video understanding since they lack effective temporal modeling and timestamp representation. In light of this, we sharpen our model by incorporating (1) an additional temporal stream to encode the relationships between frames and (2) discrete temporal tokens enriched with specific time knowledge to represent timestamps. To optimize the training of Grounded-VideoLLM, we employ a multi-stage training scheme, beginning with simple video-captioning tasks and progressively introducing video temporal grounding tasks of increasing complexity. To further enhance Grounded-VideoLLM's temporal reasoning capability, we also curate a grounded VideoQA dataset by an automatic annotation pipeline. Extensive experiments demonstrate that Grounded-VideoLLM not only excels in fine-grained grounding tasks such as temporal sentence grounding, dense video captioning, and grounded VideoQA, but also shows great potential as a versatile video assistant for general video understanding.
Visual language tracking (VLT) has emerged as a cutting-edge research area, harnessing linguistic data to enhance algorithms with multi-modal inputs and broadening the scope of traditional single object tracking (SOT) to encompass video understanding applications. Despite this, most VLT benchmarks still depend on succinct, human-annotated text descriptions for each video. These descriptions often fall short in capturing the nuances of video content dynamics and lack stylistic variety in language, constrained by their uniform level of detail and a fixed annotation frequency. As a result, algorithms tend to default to a "memorize the answer" strategy, diverging from the core objective of achieving a deeper understanding of video content. Fortunately, the emergence of large language models (LLMs) has enabled the generation of diverse text. This work utilizes LLMs to generate varied semantic annotations (in terms of text lengths and granularities) for representative SOT benchmarks, thereby establishing a novel multi-modal benchmark. Specifically, we (1) propose a new visual language tracking benchmark with diverse texts, named DTVLT, based on five prominent VLT and SOT benchmarks, including three sub-tasks: short-term tracking, long-term tracking, and global instance tracking. (2) We offer four granularity texts in our benchmark, considering the extent and density of semantic information. We expect this multi-granular generation strategy to foster a favorable environment for VLT and video understanding research. (3) We conduct comprehensive experimental analyses on DTVLT, evaluating the impact of diverse text on tracking performance and hope the identified performance bottlenecks of existing algorithms can support further research in VLT and video understanding. The proposed benchmark, experimental results and toolkit will be released gradually on http://videocube.aitestunion.com/.
Accurately identifying, understanding and describing traffic safety-critical events (SCEs), including crashes, tire strikes, and near-crashes, is crucial for advanced driver assistance systems, automated driving systems, and traffic safety. As SCEs are rare events, most general vision-language models (VLMs) have not been trained sufficiently to link SCE videos and narratives, which could lead to hallucinations and missing key safety characteristics. Here, we introduce ScVLM, a novel hybrid methodology that integrates supervised and contrastive learning techniques to classify the severity and types of SCEs, as well as to generate narrative descriptions of SCEs. This approach utilizes classification to enhance VLMs' comprehension of driving videos and improve the rationality of event descriptions. The proposed approach is trained on and evaluated by more than 8,600 SCEs from the Second Strategic Highway Research Program Naturalistic Driving Study dataset, the largest publicly accessible driving dataset with videos and SCE annotations. The results demonstrate the superiority of the proposed approach in generating contextually accurate event descriptions and mitigating VLM hallucinations. The code will be available at https://github.com/datadrivenwheels/ScVLM.
The task of action spotting consists in both identifying actions and precisely localizing them in time with a single timestamp in long, untrimmed video streams. Automatically extracting those actions is crucial for many sports applications, including sports analytics to produce extended statistics on game actions, coaching to provide support to video analysts, or fan engagement to automatically overlay content in the broadcast when specific actions occur. However, before 2018, no large-scale datasets for action spotting in sports were publicly available, which impeded benchmarking action spotting methods. In response, our team built the largest dataset and the most comprehensive benchmarks for sports video understanding, under the umbrella of SoccerNet. Particularly, our dataset contains a subset specifically dedicated to action spotting, called SoccerNet Action Spotting, containing more than 550 complete broadcast games annotated with almost all types of actions that can occur in a football game. This dataset is tailored to develop methods for automatic spotting of actions of interest, including deep learning approaches, by providing a large amount of manually annotated actions. To engage with the scientific community, the SoccerNet initiative organizes yearly challenges, during which participants from all around the world compete to achieve state-of-the-art performances. Thanks to our dataset and challenges, more than 60 methods were developed or published over the past five years, improving on the first baselines and making action spotting a viable option for the sports industry. This paper traces the history of action spotting in sports, from the creation of the task back in 2018, to the role it plays today in research and the sports industry.
Localizing unusual activities, such as human errors or surveillance incidents, in videos holds practical significance. However, current video understanding models struggle with localizing these unusual events likely because of their insufficient representation in models' pretraining datasets. To explore foundation models' capability in localizing unusual activity, we introduce UAL-Bench, a comprehensive benchmark for unusual activity localization, featuring three video datasets: UAG-OOPS, UAG-SSBD, UAG-FunQA, and an instruction-tune dataset: OOPS-UAG-Instruct, to improve model capabilities. UAL-Bench evaluates three approaches: Video-Language Models (Vid-LLMs), instruction-tuned Vid-LLMs, and a novel integration of Vision-Language Models and Large Language Models (VLM-LLM). Our results show the VLM-LLM approach excels in localizing short-span unusual events and predicting their onset (start time) more accurately than Vid-LLMs. We also propose a new metric, R@1, TD <= p, to address limitations in existing evaluation methods. Our findings highlight the challenges posed by long-duration videos, particularly in autism diagnosis scenarios, and the need for further advancements in localization techniques. Our work not only provides a benchmark for unusual activity localization but also outlines the key challenges for existing foundation models, suggesting future research directions on this important task.
We present MM1.5, a new family of multimodal large language models (MLLMs) designed to enhance capabilities in text-rich image understanding, visual referring and grounding, and multi-image reasoning. Building upon the MM1 architecture, MM1.5 adopts a data-centric approach to model training, systematically exploring the impact of diverse data mixtures across the entire model training lifecycle. This includes high-quality OCR data and synthetic captions for continual pre-training, as well as an optimized visual instruction-tuning data mixture for supervised fine-tuning. Our models range from 1B to 30B parameters, encompassing both dense and mixture-of-experts (MoE) variants, and demonstrate that careful data curation and training strategies can yield strong performance even at small scales (1B and 3B). Additionally, we introduce two specialized variants: MM1.5-Video, designed for video understanding, and MM1.5-UI, tailored for mobile UI understanding. Through extensive empirical studies and ablations, we provide detailed insights into the training processes and decisions that inform our final designs, offering valuable guidance for future research in MLLM development.
In the video-language domain, recent works in leveraging zero-shot Large Language Model-based reasoning for video understanding have become competitive challengers to previous end-to-end models. However, long video understanding presents unique challenges due to the complexity of reasoning over extended timespans, even for zero-shot LLM-based approaches. The challenge of information redundancy in long videos prompts the question of what specific information is essential for large language models (LLMs) and how to leverage them for complex spatial-temporal reasoning in long-form video analysis. We propose a framework VideoINSTA, i.e. INformative Spatial-TemporAl Reasoning for zero-shot long-form video understanding. VideoINSTA contributes (1) a zero-shot framework for long video understanding using LLMs; (2) an event-based temporal reasoning and content-based spatial reasoning approach for LLMs to reason over spatial-temporal information in videos; (3) a self-reflective information reasoning scheme balancing temporal factors based on information sufficiency and prediction confidence. Our model significantly improves the state-of-the-art on three long video question-answering benchmarks: EgoSchema, NextQA, and IntentQA, and the open question answering dataset ActivityNetQA. The code is released here: https://github.com/mayhugotong/VideoINSTA.
With the rising interest in research on Large Multi-modal Models (LMMs) for video understanding, many studies have emphasized general video comprehension capabilities, neglecting the systematic exploration into video quality understanding. To address this oversight, we introduce Q-Bench-Video in this paper, a new benchmark specifically designed to evaluate LMMs' proficiency in discerning video quality. a) To ensure video source diversity, Q-Bench-Video encompasses videos from natural scenes, AI-generated Content (AIGC), and Computer Graphics (CG). b) Building on the traditional multiple-choice questions format with the Yes-or-No and What-How categories, we include Open-ended questions to better evaluate complex scenarios. Additionally, we incorporate the video pair quality comparison question to enhance comprehensiveness. c) Beyond the traditional Technical, Aesthetic, and Temporal distortions, we have expanded our evaluation aspects to include the dimension of AIGC distortions, which addresses the increasing demand for video generation. Finally, we collect a total of 2,378 question-answer pairs and test them on 12 open-source & 5 proprietary LMMs. Our findings indicate that while LMMs have a foundational understanding of video quality, their performance remains incomplete and imprecise, with a notable discrepancy compared to human performance. Through Q-Bench-Video, we seek to catalyze community interest, stimulate further research, and unlock the untapped potential of LMMs to close the gap in video quality understanding.
Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding capabilities in modeling long texts. Existing work attempts to address this issue by introducing long video-text pairs during training. However, these approaches require substantial computational and data resources. In this paper, we tackle the challenge of long video understanding from the perspective of context windows, aiming to apply LMMs to long video tasks without retraining on long video datasets. We first conduct an in-depth analysis of why pretrained LMMs struggle to understand lengthy video content, identifying that discrepancies between visual and language modalities lead to different context windows for visual and language tokens, making it difficult to directly extend the visual tokens to match the language context window. Based on this, we propose to adapt LMMs for long video understanding tasks by extending the visual context window, eliminating the need for retraining on large scalelong video datasets. To further mitigate the significant memory consumption caused by long sequences, we introduce a progressive pooling inference strategy that selectively adjusts the spatial resolution of frame embeddings, reducing the number of visual tokens while retaining important spatial information. Across multiple long video understanding benchmarks, our method consistently improves the performance as the number of video frames increases. On the MLVU benchmark, our method outperforms GPT-4o, even though our model size is only 7B. Additionally, in the 256-frame setting, our method reduces memory usage by approximately 45% compared to the baseline, without introducing any performance loss.
With the development of video understanding, there is a proliferation of tasks for clip-level temporal video analysis, including temporal action detection (TAD), temporal action segmentation (TAS), and generic event boundary detection (GEBD). While task-specific video understanding models have exhibited outstanding performance in each task, there remains a dearth of a unified framework capable of simultaneously addressing multiple tasks, which is a promising direction for the next generation of AI. To this end, in this paper, we propose a single unified framework, coined as Temporal2Seq, to formulate the output of these temporal video understanding tasks as a sequence of discrete tokens. With this unified token representation, Temporal2Seq can train a generalist model within a single architecture on different video understanding tasks. In the absence of multi-task learning (MTL) benchmarks, we compile a comprehensive co-training dataset by borrowing the datasets from TAD, TAS, and GEBD tasks. We evaluate our Temporal2Seq generalist model on the corresponding test sets of three tasks, demonstrating that Temporal2Seq can produce reasonable results on various tasks and achieve advantages compared with single-task training on this framework. We also investigate the generalization performance of our generalist model on new datasets from different tasks, which yields superior performance to the specific model.
The integration of Large Language Models (LLMs) with visual encoders has recently shown promising performance in visual understanding tasks, leveraging their inherent capability to comprehend and generate human-like text for visual reasoning. Given the diverse nature of visual data, MultiModal Large Language Models (MM-LLMs) exhibit variations in model designing and training for understanding images, short videos, and long videos. Our paper focuses on the substantial differences and unique challenges posed by long video understanding compared to static image and short video understanding. Unlike static images, short videos encompass sequential frames with both spatial and within-event temporal information, while long videos consist of multiple events with between-event and long-term temporal information. In this survey, we aim to trace and summarize the advancements of MM-LLMs from image understanding to long video understanding. We review the differences among various visual understanding tasks and highlight the challenges in long video understanding, including more fine-grained spatiotemporal details, dynamic events, and long-term dependencies. We then provide a detailed summary of the advancements in MM-LLMs in terms of model design and training methodologies for understanding long videos. Finally, we compare the performance of existing MM-LLMs on video understanding benchmarks of various lengths and discuss potential future directions for MM-LLMs in long video understanding.
Recent advances in Video Large Language Models (Video-LLMs) have demonstrated their great potential in general-purpose video understanding. To verify the significance of these models, a number of benchmarks have been proposed to diagnose their capabilities in different scenarios. However, existing benchmarks merely evaluate models through video-level question-answering, lacking fine-grained event-level assessment and task diversity. To fill this gap, we introduce E.T. Bench (Event-Level & Time-Sensitive Video Understanding Benchmark), a large-scale and high-quality benchmark for open-ended event-level video understanding. Categorized within a 3-level task taxonomy, E.T. Bench encompasses 7.3K samples under 12 tasks with 7K videos (251.4h total length) under 8 domains, providing comprehensive evaluations. We extensively evaluated 8 Image-LLMs and 12 Video-LLMs on our benchmark, and the results reveal that state-of-the-art models for coarse-level (video-level) understanding struggle to solve our fine-grained tasks, e.g., grounding event-of-interests within videos, largely due to the short video context length, improper time representations, and lack of multi-event training data. Focusing on these issues, we further propose a strong baseline model, E.T. Chat, together with an instruction-tuning dataset E.T. Instruct 164K tailored for fine-grained event-level understanding. Our simple but effective solution demonstrates superior performance in multiple scenarios.
Decoding visual-semantic information from brain signals, such as functional MRI (fMRI), across different subjects poses significant challenges, including low signal-to-noise ratio, limited data availability, and cross-subject variability. Recent advancements in large language models (LLMs) show remarkable effectiveness in processing multimodal information. In this study, we introduce an LLM-based approach for reconstructing visual-semantic information from fMRI signals elicited by video stimuli. Specifically, we employ fine-tuning techniques on an fMRI encoder equipped with adaptors to transform brain responses into latent representations aligned with the video stimuli. Subsequently, these representations are mapped to textual modality by LLM. In particular, we integrate self-supervised domain adaptation methods to enhance the alignment between visual-semantic information and brain responses. Our proposed method achieves good results using various quantitative semantic metrics, while yielding similarity with ground-truth information.
The rapid evolution of egocentric video analysis brings new insights into understanding human activities and intentions from a first-person perspective. Despite this progress, the fragmentation in tasks like action recognition, procedure learning, and moment retrieval, \etc, coupled with inconsistent annotations and isolated model development, hinders a holistic interpretation of video content. In response, we introduce the EAGLE (Egocentric AGgregated Language-video Engine) model and the EAGLE-400K dataset to provide a unified framework that integrates various egocentric video understanding tasks. EAGLE-400K, the \textit{first} large-scale instruction-tuning dataset tailored for egocentric video, features 400K diverse samples to enhance a broad spectrum of tasks from activity recognition to procedure knowledge learning. Moreover, EAGLE, a strong video multimodal large language model (MLLM), is designed to effectively capture both spatial and temporal information. In addition, we propose a set of evaluation metrics designed to facilitate a thorough assessment of MLLM for egocentric video understanding. Our extensive experiments demonstrate EAGLE's superior performance over existing models, highlighting its ability to balance task-specific understanding with holistic video interpretation. With EAGLE, we aim to pave the way for research opportunities and practical applications in real-world scenarios.
Clinical videos in the context of Autism Spectrum Disorder are often long-form interactions between children and caregivers/clinical professionals, encompassing complex verbal and non-verbal behaviors. Objective analyses of these videos could provide clinicians and researchers with nuanced insights into the behavior of children with Autism Spectrum Disorder. Manually coding these videos is a time-consuming task and requires a high level of domain expertise. Hence, the ability to capture these interactions computationally can augment the manual effort and enable supporting the diagnostic procedure. In this work, we investigate the use of foundation models across three modalities: speech, video, and text, to analyse child-focused interaction sessions. We propose a unified methodology to combine multiple modalities by using large language models as reasoning agents. We evaluate their performance on two tasks with different information granularity: activity recognition and abnormal behavior detection. We find that the proposed multimodal pipeline provides robustness to modality-specific limitations and improves performance on the clinical video analysis compared to unimodal settings.
In this report, we present our first-place solution to the Multiple-choice Video Question Answering (QA) track of The Second Perception Test Challenge. This competition posed a complex video understanding task, requiring models to accurately comprehend and answer questions about video content. To address this challenge, we leveraged the powerful QwenVL2 (7B) model and fine-tune it on the provided training set. Additionally, we employed model ensemble strategies and Test Time Augmentation to boost performance. Through continuous optimization, our approach achieved a Top-1 Accuracy of 0.7647 on the leaderboard.
Long video understanding poses a significant challenge for current Multi-modal Large Language Models (MLLMs). Notably, the MLLMs are constrained by their limited context lengths and the substantial costs while processing long videos. Although several existing methods attempt to reduce visual tokens, their strategies encounter severe bottleneck, restricting MLLMs' ability to perceive fine-grained visual details. In this work, we propose Video-XL, a novel approach that leverages MLLMs' inherent key-value (KV) sparsification capacity to condense the visual input. Specifically, we introduce a new special token, the Visual Summarization Token (VST), for each interval of the video, which summarizes the visual information within the interval as its associated KV. The VST module is trained by instruction fine-tuning, where two optimizing strategies are offered. 1.Curriculum learning, where VST learns to make small (easy) and large compression (hard) progressively. 2. Composite data curation, which integrates single-image, multi-image, and synthetic data to overcome the scarcity of long-video instruction data. The compression quality is further improved by dynamic compression, which customizes compression granularity based on the information density of different video intervals. Video-XL's effectiveness is verified from three aspects. First, it achieves a superior long-video understanding capability, outperforming state-of-the-art models of comparable sizes across multiple popular benchmarks. Second, it effectively preserves video information, with minimal compression loss even at 16x compression ratio. Third, it realizes outstanding cost-effectiveness, enabling high-quality processing of thousands of frames on a single A100 GPU.
CLIP has demonstrated great versatility in adapting to various downstream tasks, such as image editing and generation, visual question answering, and video understanding. However, CLIP-based applications often suffer from misunderstandings regarding user intent, leading to discrepancies between the required number of objects and the actual outputs in image generation tasks. In this work, we empirically investigate the quantity bias in CLIP. By carefully designing different experimental settings and datasets, we comprehensively evaluate CLIP's understanding of quantity from text, image, and cross-modal perspectives. Our experimental results reveal a quantity bias in CLIP embeddings, impacting the reliability of downstream tasks.
Video annotation is a critical and time-consuming task in computer vision research and applications. This paper presents a novel annotation pipeline that uses pre-extracted features and dimensionality reduction to accelerate the temporal video annotation process. Our approach uses Hierarchical Stochastic Neighbor Embedding (HSNE) to create a multi-scale representation of video features, allowing annotators to efficiently explore and label large video datasets. We demonstrate significant improvements in annotation effort compared to traditional linear methods, achieving more than a 10x reduction in clicks required for annotating over 12 hours of video. Our experiments on multiple datasets show the effectiveness and robustness of our pipeline across various scenarios. Moreover, we investigate the optimal configuration of HSNE parameters for different datasets. Our work provides a promising direction for scaling up video annotation efforts in the era of video understanding.
The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding, field understanding, and player understanding. This year, the challenges encompass four vision-based tasks. (1) Ball Action Spotting, focusing on precisely localizing when and which soccer actions related to the ball occur, (2) Dense Video Captioning, focusing on describing the broadcast with natural language and anchored timestamps, (3) Multi-View Foul Recognition, a novel task focusing on analyzing multiple viewpoints of a potential foul incident to classify whether a foul occurred and assess its severity, (4) Game State Reconstruction, another novel task focusing on reconstructing the game state from broadcast videos onto a 2D top-view map of the field. Detailed information about the tasks, challenges, and leaderboards can be found at https://www.soccer-net.org, with baselines and development kits available at https://github.com/SoccerNet.