LLaFEA: Frame-Event Complementary Fusion for Fine-Grained Spatiotemporal Understanding in LMMs

• URL: http://arxiv.org/abs/2503.06934v1
• Date: Mon, 10 Mar 2025 05:30:30 GMT
• Title: LLaFEA: Frame-Event Complementary Fusion for Fine-Grained Spatiotemporal Understanding in LMMs
• Authors: Hanyu Zhou, Gim Hee Lee,
• Abstract summary: Large models (LMMs) excel in scene understanding but struggle with fine-temporal reasoning due to weak alignment between linguistic and visual representations.<n>Existing methods map textual positions and durations into the visual space from frame-based videos, but suffer from temporal sparsity that limits temporal coordination.<n>We introduce LFEA to leverage event cameras for temporally dense perception and frame-event fusion.
• Score: 55.81291976637705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large multimodal models (LMMs) excel in scene understanding but struggle with fine-grained spatiotemporal reasoning due to weak alignment between linguistic and visual representations. Existing methods map textual positions and durations into the visual space encoded from frame-based videos, but suffer from temporal sparsity that limits language-vision temporal coordination. To address this issue, we introduce LLaFEA (Large Language and Frame-Event Assistant) to leverage event cameras for temporally dense perception and frame-event fusion. Our approach employs a cross-attention mechanism to integrate complementary spatial and temporal features, followed by self-attention matching for global spatio-temporal associations. We further embed textual position and duration tokens into the fused visual space to enhance fine-grained alignment. This unified framework ensures robust spatio-temporal coordinate alignment, enabling LMMs to interpret scenes at any position and any time. In addition, we construct a dataset of real-world frames-events with coordinate instructions and conduct extensive experiments to validate the effectiveness of the proposed method.

Related papers

• Collaborative Temporal Consistency Learning for Point-supervised Natural Language Video Localization [129.43937834515688]
  We propose a new COllaborative Temporal consistEncy Learning (COTEL) framework to strengthen the video-language alignment. Specifically, we first design a frame- and a segment-level Temporal Consistency Learning (TCL) module that models semantic alignment across frame saliencies and sentence-moment pairs.
  arXiv  Detail & Related papers  (2025-03-22T05:04:12Z)
• SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability [58.46310813774538]
  Large language models (LMLMs) have made remarkable progress in either temporal or spatial localization. However they struggle to perform-temporal video grounding. This limitation stems from two major challenges. We introduce SpaceLM, a MLLMVL endowed with temporal-temporal video grounding.
  arXiv  Detail & Related papers  (2025-03-18T07:40:36Z)
• Measure Twice, Cut Once: Grasping Video Structures and Event Semantics with LLMs for Video Temporal Localization [22.46313255627877]
  We introduce MeCo, a timestamp-free framework for temporal localization tasks. MeCo partitions videos into holistic event and transition segments based on the proposed structural token generation and grounding pipeline. We propose a query-focused captioning task that compels the LLM to extract fine-grained, event-specific details.
  arXiv  Detail & Related papers  (2025-03-12T03:33:50Z)
• LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding [29.42797944919497]
  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.
  arXiv  Detail & Related papers  (2025-01-14T17:58:12Z)
• Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP [34.88916568947695]
  We propose a novel CLI framework to comprehend multi-temporal dynamics.<n>For the vision side, we propose an efficient Dynamic Crossshot Attention.<n>For the semantic side, we conduct text augmentation by constructing an Action Knowledge Graph.
  arXiv  Detail & Related papers  (2024-12-13T06:30:52Z)
• MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval [53.417646562344906]
  Video Moment Retrieval (VMR) aims to localize a specific temporal segment within an untrimmed long video given a natural language query. Existing methods often suffer from inadequate training annotations, i.e., the sentence typically matches with a fraction of the prominent video content in the foreground with limited wording diversity. This intrinsic modality imbalance leaves a considerable portion of visual information remaining unaligned with text. In this work, we take an MLLM as a video narrator to generate plausible textual descriptions of the video, thereby mitigating the modality imbalance and boosting the temporal localization.
  arXiv  Detail & Related papers  (2024-06-25T18:39:43Z)
• MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading [23.071296603664656]
  Lip-reading is to utilize the visual information of the speaker's lip movements to recognize words and sentences.<n>We propose a novel framework termed Multi-view Temporality aligned Aggregation (MTGA)<n>Our method outperforms both the event-based and video-based lip-reading counterparts.
  arXiv  Detail & Related papers  (2024-04-18T08:16:56Z)
• SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation [35.063881868130075]
  This paper studies referring video object segmentation (RVOS) by boosting video-level visual-linguistic alignment. We propose Semantic-assisted Object Cluster (SOC), which aggregates video content and textual guidance for unified temporal modeling and cross-modal alignment. We conduct extensive experiments on popular RVOS benchmarks, and our method outperforms state-of-the-art competitors on all benchmarks by a remarkable margin.
  arXiv  Detail & Related papers  (2023-05-26T15:13:44Z)
• Implicit Temporal Modeling with Learnable Alignment for Video Recognition [95.82093301212964]
  We propose a novel Implicit Learnable Alignment (ILA) method, which minimizes the temporal modeling effort while achieving incredibly high performance. ILA achieves a top-1 accuracy of 88.7% on Kinetics-400 with much fewer FLOPs compared with Swin-L and ViViT-H.
  arXiv  Detail & Related papers  (2023-04-20T17:11:01Z)
• Local-Global Temporal Difference Learning for Satellite Video Super-Resolution [55.69322525367221]
  We propose to exploit the well-defined temporal difference for efficient and effective temporal compensation. To fully utilize the local and global temporal information within frames, we systematically modeled the short-term and long-term temporal discrepancies. Rigorous objective and subjective evaluations conducted across five mainstream video satellites demonstrate that our method performs favorably against state-of-the-art approaches.
  arXiv  Detail & Related papers  (2023-04-10T07:04:40Z)
• Learning Commonsense-aware Moment-Text Alignment for Fast Video Temporal Grounding [78.71529237748018]
  Grounding temporal video segments described in natural language queries effectively and efficiently is a crucial capability needed in vision-and-language fields. Most existing approaches adopt elaborately designed cross-modal interaction modules to improve the grounding performance. We propose a commonsense-aware cross-modal alignment framework, which incorporates commonsense-guided visual and text representations into a complementary common space.
  arXiv  Detail & Related papers  (2022-04-04T13:07:05Z)
• Learning by Aligning Videos in Time [10.075645944474287]
  We present a self-supervised approach for learning video representations using temporal video alignment as a pretext task. We leverage a novel combination of temporal alignment loss and temporal regularization terms, which can be used as supervision signals for training an encoder network.
  arXiv  Detail & Related papers  (2021-03-31T17:55:52Z)

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.