With the burgeoning growth of online video platforms and the escalating volume of video content, the demand for proficient video understanding tools has intensified markedly. Given the remarkable capabilities of Large Language Models (LLMs) in language and multimodal tasks, this survey provides a detailed overview of the recent advancements in video understanding harnessing the power of LLMs (Vid-LLMs). The emergent capabilities of Vid-LLMs are surprisingly advanced, particularly their ability for open-ended spatial-temporal reasoning combined with commonsense knowledge, suggesting a promising path for future video understanding. We examine the unique characteristics and capabilities of Vid-LLMs, categorizing the approaches into four main types: LLM-based Video Agents, Vid-LLMs Pretraining, Vid-LLMs Instruction Tuning, and Hybrid Methods. Furthermore, this survey presents a comprehensive study of the tasks, datasets, and evaluation methodologies for Vid-LLMs. Additionally, it explores the expansive applications of Vid-LLMs across various domains, highlighting their remarkable scalability and versatility in real-world video understanding challenges. Finally, it summarizes the limitations of existing Vid-LLMs and outlines directions for future research. For more information, readers are recommended to visit the repository at //github.com/yunlong10/Awesome-LLMs-for-Video-Understanding.
相關內容
We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities, including speech, text, images, and music. AnyGPT can be trained stably without any alterations to the current large language model (LLM) architecture or training paradigms. Instead, it relies exclusively on data-level preprocessing, facilitating the seamless integration of new modalities into LLMs, akin to the incorporation of new languages. We build a multimodal text-centric dataset for multimodal alignment pre-training. Utilizing generative models, we synthesize the first large-scale any-to-any multimodal instruction dataset. It consists of 108k samples of multi-turn conversations that intricately interweave various modalities, thus equipping the model to handle arbitrary combinations of multimodal inputs and outputs. Experimental results demonstrate that AnyGPT is capable of facilitating any-to-any multimodal conversation while achieving performance comparable to specialized models across all modalities, proving that discrete representations can effectively and conveniently unify multiple modalities within a language model. Demos are shown in //junzhan2000.github.io/AnyGPT.github.io/
Recent LLM-driven visual agents mainly focus on solving image-based tasks, which limits their ability to understand dynamic scenes, making it far from real-life applications like guiding students in laboratory experiments and identifying their mistakes. Considering the video modality better reflects the ever-changing nature of real-world scenarios, we devise DoraemonGPT, a comprehensive and conceptually elegant system driven by LLMs to handle dynamic video tasks. Given a video with a question/task, DoraemonGPT begins by converting the input video into a symbolic memory that stores task-related attributes. This structured representation allows for spatial-temporal querying and reasoning by well-designed sub-task tools, resulting in concise intermediate results. Recognizing that LLMs have limited internal knowledge when it comes to specialized domains (e.g., analyzing the scientific principles underlying experiments), we incorporate plug-and-play tools to assess external knowledge and address tasks across different domains. Moreover, a novel LLM-driven planner based on Monte Carlo Tree Search is introduced to explore the large planning space for scheduling various tools. The planner iteratively finds feasible solutions by backpropagating the result's reward, and multiple solutions can be summarized into an improved final answer. We extensively evaluate DoraemonGPT's effectiveness on three benchmarks and challenging in-the-wild scenarios. Code will be released at: //github.com/z-x-yang/DoraemonGPT.
The rise of multimodal misinformation on social platforms poses significant challenges for individuals and societies. Its increased credibility and broader impact compared to textual misinformation make detection complex, requiring robust reasoning across diverse media types and profound knowledge for accurate verification. The emergence of Large Vision Language Model (LVLM) offers a potential solution to this problem. Leveraging their proficiency in processing visual and textual information, LVLM demonstrates promising capabilities in recognizing complex information and exhibiting strong reasoning skills. In this paper, we first investigate the potential of LVLM on multimodal misinformation detection. We find that even though LVLM has a superior performance compared to LLMs, its profound reasoning may present limited power with a lack of evidence. Based on these observations, we propose LEMMA: LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation. LEMMA leverages LVLM intuition and reasoning capabilities while augmenting them with external knowledge to enhance the accuracy of misinformation detection. Our method improves the accuracy over the top baseline LVLM by 7% and 13% on Twitter and Fakeddit datasets respectively.
In this paper, a novel amplitude phase shift keying (APSK) modulation scheme for cooperative backscatter communications aided by a reconfigurable intelligent surface (RIS-CBC) is presented, according to which the RIS is configured to modulate backscatter information onto unmodulated or PSK-modulated signals impinging on its surface via APSK. We consider both passive and active RISs, with the latter including an amplification unit at each reflecting element. In the passive (resp. active) RIS-CBC-APSK, backscatter information is conveyed through the number of RIS reflecting elements being on the ON state (resp. active mode) and their phase shift values. By using the optimal APSK constellation to ensure that reflected signals from the RIS undergo APSK modulation, a bit-mapping mechanism is presented. Assuming maximum-likelihood detection, we also present closed-form upper bounds for the symbol error rate (SER) performance for both passive and active RIS-CBC-APSK schemes over Rician fading channels. In addition, we devise a low-complexity detector that can achieve flexible trade-offs between performance and complexity. Finally, we extend RIS-CBC-APSK to multiple-input single-output scenarios and present an alternating optimization approach for the joint design of transmit beamforming and RIS reflection. Our extensive simulation results on the SER performance corroborate our conducted performance analysis and showcase the superiority of the proposed RIS-CBC-APSK schemes over the state-of-the-art RIS-CBC benchmarks.
We marry diffusion policies and 3D scene representations for robot manipulation. Diffusion policies learn the action distribution conditioned on the robot and environment state using conditional diffusion models. They have recently shown to outperform both deterministic and alternative state-conditioned action distribution learning methods. 3D robot policies use 3D scene feature representations aggregated from a single or multiple camera views using sensed depth. They have shown to generalize better than their 2D counterparts across camera viewpoints. We unify these two lines of work and present 3D Diffuser Actor, a neural policy architecture that, given a language instruction, builds a 3D representation of the visual scene and conditions on it to iteratively denoise 3D rotations and translations for the robot's end-effector. At each denoising iteration, our model represents end-effector pose estimates as 3D scene tokens and predicts the 3D translation and rotation error for each of them, by featurizing them using 3D relative attention to other 3D visual and language tokens. 3D Diffuser Actor sets a new state-of-the-art on RLBench with an absolute performance gain of 16.3% over the current SOTA on a multi-view setup and an absolute gain of 13.1% on a single-view setup. On the CALVIN benchmark, it outperforms the current SOTA in the setting of zero-shot unseen scene generalization by being able to successfully run 0.2 more tasks, a 7% relative increase. It also works in the real world from a handful of demonstrations. We ablate our model's architectural design choices, such as 3D scene featurization and 3D relative attentions, and show they all help generalization. Our results suggest that 3D scene representations and powerful generative modeling are keys to efficient robot learning from demonstrations.
We present, PEGASUS, a method for constructing personalized generative 3D face avatars from monocular video sources. As a compositional generative model, our model enables disentangled controls to selectively alter the facial attributes (e.g., hair or nose) of the target individual, while preserving the identity. We present two key approaches to achieve this goal. First, we present a method to construct a person-specific generative 3D avatar by building a synthetic video collection of the target identity with varying facial attributes, where the videos are synthesized by borrowing parts from diverse individuals from other monocular videos. Through several experiments, we demonstrate the superior performance of our approach by generating unseen attributes with high realism. Subsequently, we introduce a zero-shot approach to achieve the same generative modeling more efficiently by leveraging a previously constructed personalized generative model.
With the extremely rapid advances in remote sensing (RS) technology, a great quantity of Earth observation (EO) data featuring considerable and complicated heterogeneity is readily available nowadays, which renders researchers an opportunity to tackle current geoscience applications in a fresh way. With the joint utilization of EO data, much research on multimodal RS data fusion has made tremendous progress in recent years, yet these developed traditional algorithms inevitably meet the performance bottleneck due to the lack of the ability to comprehensively analyse and interpret these strongly heterogeneous data. Hence, this non-negligible limitation further arouses an intense demand for an alternative tool with powerful processing competence. Deep learning (DL), as a cutting-edge technology, has witnessed remarkable breakthroughs in numerous computer vision tasks owing to its impressive ability in data representation and reconstruction. Naturally, it has been successfully applied to the field of multimodal RS data fusion, yielding great improvement compared with traditional methods. This survey aims to present a systematic overview in DL-based multimodal RS data fusion. More specifically, some essential knowledge about this topic is first given. Subsequently, a literature survey is conducted to analyse the trends of this field. Some prevalent sub-fields in the multimodal RS data fusion are then reviewed in terms of the to-be-fused data modalities, i.e., spatiospectral, spatiotemporal, light detection and ranging-optical, synthetic aperture radar-optical, and RS-Geospatial Big Data fusion. Furthermore, We collect and summarize some valuable resources for the sake of the development in multimodal RS data fusion. Finally, the remaining challenges and potential future directions are highlighted.
This paper introduces video domain generalization where most video classification networks degenerate due to the lack of exposure to the target domains of divergent distributions. We observe that the global temporal features are less generalizable, due to the temporal domain shift that videos from other unseen domains may have an unexpected absence or misalignment of the temporal relations. This finding has motivated us to solve video domain generalization by effectively learning the local-relation features of different timescales that are more generalizable, and exploiting them along with the global-relation features to maintain the discriminability. This paper presents the VideoDG framework with two technical contributions. The first is a new deep architecture named the Adversarial Pyramid Network, which improves the generalizability of video features by capturing the local-relation, global-relation, and cross-relation features progressively. On the basis of pyramid features, the second contribution is a new and robust approach of adversarial data augmentation that can bridge different video domains by improving the diversity and quality of augmented data. We construct three video domain generalization benchmarks in which domains are divided according to different datasets, different consequences of actions, or different camera views, respectively. VideoDG consistently outperforms the combinations of previous video classification models and existing domain generalization methods on all benchmarks.
The accurate and interpretable prediction of future events in time-series data often requires the capturing of representative patterns (or referred to as states) underpinning the observed data. To this end, most existing studies focus on the representation and recognition of states, but ignore the changing transitional relations among them. In this paper, we present evolutionary state graph, a dynamic graph structure designed to systematically represent the evolving relations (edges) among states (nodes) along time. We conduct analysis on the dynamic graphs constructed from the time-series data and show that changes on the graph structures (e.g., edges connecting certain state nodes) can inform the occurrences of events (i.e., time-series fluctuation). Inspired by this, we propose a novel graph neural network model, Evolutionary State Graph Network (EvoNet), to encode the evolutionary state graph for accurate and interpretable time-series event prediction. Specifically, Evolutionary State Graph Network models both the node-level (state-to-state) and graph-level (segment-to-segment) propagation, and captures the node-graph (state-to-segment) interactions over time. Experimental results based on five real-world datasets show that our approach not only achieves clear improvements compared with 11 baselines, but also provides more insights towards explaining the results of event predictions.
This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory (LSTM) layers to create an interweaved recurrent-convolutional architecture. Additionally, we propose an efficient Bottleneck-LSTM layer that significantly reduces computational cost compared to regular LSTMs. Our network achieves temporal awareness by using Bottleneck-LSTMs to refine and propagate feature maps across frames. This approach is substantially faster than existing detection methods in video, outperforming the fastest single-frame models in model size and computational cost while attaining accuracy comparable to much more expensive single-frame models on the Imagenet VID 2015 dataset. Our model reaches a real-time inference speed of up to 15 FPS on a mobile CPU.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191