LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding

• URL: http://arxiv.org/abs/2501.08282v1
• Date: Tue, 14 Jan 2025 17:58:12 GMT
• Title: LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
• Authors: Hongyu Li, Jinyu Chen, Ziyu Wei, Shaofei Huang, Tianrui Hui, Jialin Gao, Xiaoming Wei, Si Liu,
• Abstract summary: We propose LLaVA-ST, a MLLM for fine-grained spatial-temporal multimodal understanding. In LLaVA-ST, we propose Language-Aligned Positional Embedding, which embeds the coordinate special token into the visual space. We also design the Spatial-Temporal Packer, which decouples the feature compression of temporal and spatial resolutions into two distinct point-to-region attention processing streams.
• Score: 29.42797944919497
• License:
• Abstract: Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge stems from two key issues: first, incorporating spatial-temporal localization introduces a vast number of coordinate combinations, complicating the alignment of linguistic and visual coordinate representations; second, encoding fine-grained temporal and spatial information during video feature compression is inherently difficult. To address these issues, we propose LLaVA-ST, a MLLM for fine-grained spatial-temporal multimodal understanding. In LLaVA-ST, we propose Language-Aligned Positional Embedding, which embeds the textual coordinate special token into the visual space, simplifying the alignment of fine-grained spatial-temporal correspondences. Additionally, we design the Spatial-Temporal Packer, which decouples the feature compression of temporal and spatial resolutions into two distinct point-to-region attention processing streams. Furthermore, we propose ST-Align dataset with 4.3M training samples for fine-grained spatial-temporal multimodal understanding. With ST-align, we present a progressive training pipeline that aligns the visual and textual feature through sequential coarse-to-fine stages.Additionally, we introduce an ST-Align benchmark to evaluate spatial-temporal interleaved fine-grained understanding tasks, which include Spatial-Temporal Video Grounding (STVG) , Event Localization and Captioning (ELC) and Spatial Video Grounding (SVG). LLaVA-ST achieves outstanding performance on 11 benchmarks requiring fine-grained temporal, spatial, or spatial-temporal interleaving multimodal understanding. Our code, data and benchmark will be released at Our code, data and benchmark will be released at https://github.com/appletea233/LLaVA-ST .

Related papers

• STNMamba: Mamba-based Spatial-Temporal Normality Learning for Video Anomaly Detection [48.997518615379995]
  Video anomaly detection (VAD) has been extensively researched due to its potential for intelligent video systems. Most existing methods based on CNNs and transformers still suffer from substantial computational burdens. We propose a lightweight and effective Mamba-based network named STNMamba to enhance the learning of spatial-temporal normality.
  arXiv  Detail & Related papers  (2024-12-28T08:49:23Z)
• Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model [51.83436609094658]
  We introduce Coarse Correspondences, a simple lightweight method that enhances MLLMs' spatial-temporal reasoning with 2D images as input. Our method uses a lightweight tracking model to identify primary object correspondences between frames in a video or across different image viewpoints. We demonstrate that this simple training-free approach brings substantial gains to GPT4-V/O consistently on four benchmarks.
  arXiv  Detail & Related papers  (2024-08-01T17:57:12Z)
• Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion [57.232688209606515]
  We present HTCL, a novel Temporal Temporal Context Learning paradigm for improving camera-based semantic scene completion. Our method ranks $1st$ on the Semantic KITTI benchmark and even surpasses LiDAR-based methods in terms of mIoU.
  arXiv  Detail & Related papers  (2024-07-02T09:11:17Z)
• Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment [130.15775113897553]
  Finsta is a fine-grained structural-temporal alignment learning method. It consistently improves the existing 13 strong-tuning video-language models.
  arXiv  Detail & Related papers  (2024-06-27T15:23:36Z)
• $\textbf{S}^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting [21.921303835714628]
  We propose Semantic Space Informed Prompt learning with LLM ($S2$IP-LLM) to align the pre-trained semantic space with time series embeddings space. We show that the proposed $S2$IP-LLM can achieve superior forecasting performance over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-03-09T05:20:48Z)
• How Can Large Language Models Understand Spatial-Temporal Data? [12.968952073740796]
  This paper introduces STG-LLM, an innovative approach empowering Large Language Models for spatial-temporal forecasting. We tackle the data mismatch by proposing: 1) STG-Tokenizer: This spatial-temporal graph tokenizer transforms intricate graph data into concise tokens capturing both spatial and temporal relationships; 2) STG-Adapter: This minimalistic adapter, consisting of linear encoding and decoding layers, bridges the gap between tokenized data and LLM comprehension.
  arXiv  Detail & Related papers  (2024-01-25T14:03:15Z)
• Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding [112.3913646778859]
  We propose a simple yet effective video-language modeling framework, S-ViLM. It includes two novel designs, inter-clip spatial grounding and intra-clip temporal grouping, to promote learning region-object alignment and temporal-aware features. S-ViLM surpasses the state-of-the-art methods substantially on four representative downstream tasks.
  arXiv  Detail & Related papers  (2023-03-28T22:45:07Z)
• Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction [36.77135502344546]
  We propose a novel Spatio-Supervised Learning (ST-SSL) traffic prediction framework. Our ST-SSL is built over an integrated module with temporal spatial convolutions for encoding the information across space and time. Experiments on four benchmark datasets demonstrate that ST-SSL consistently outperforms various state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-12-07T10:02:01Z)
• Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation [28.472006665544033]
  Referring video object segmentation aims to predict foreground labels for objects referred by natural language expressions in videos. Previous methods either depend on 3D ConvNets or incorporate additional 2D ConvNets as encoders to extract mixed spatial-temporal features. We propose a Language-Bridged Duplex Transfer (LBDT) module which utilizes language as an intermediary bridge to accomplish explicit and adaptive spatial-temporal interaction earlier in the encoding phase.
  arXiv  Detail & Related papers  (2022-06-08T10:12:53Z)
• BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues [95.8297116307127]
  We propose Bi-directional Spatio-Temporal Learning (BiST), a vision-language neural framework for high-resolution queries in videos. Specifically, our approach exploits both spatial and temporal-level information, and learns dynamic information diffusion between the two feature spaces. BiST achieves competitive performance and generates reasonable responses on a large-scale AVSD benchmark.
  arXiv  Detail & Related papers  (2020-10-20T07:43:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.