SceneLLM: Implicit Language Reasoning in LLM for Dynamic Scene Graph Generation

• URL: http://arxiv.org/abs/2412.11026v1
• Date: Sun, 15 Dec 2024 02:41:31 GMT
• Title: SceneLLM: Implicit Language Reasoning in LLM for Dynamic Scene Graph Generation
• Authors: Hang Zhang, Zhuoling Li, Jun Liu,
• Abstract summary: SceneLLM is a framework that transforms video frames into linguistic signals (scene tokens) Our method achieves state-of-the-art results on the Action Genome (AG) benchmark. Extensive experiments show the effectiveness of SceneLLM in understanding and generating accurate dynamic scene graphs.
• Score: 8.768484848591168
• License:
• Abstract: Dynamic scenes contain intricate spatio-temporal information, crucial for mobile robots, UAVs, and autonomous driving systems to make informed decisions. Parsing these scenes into semantic triplets <Subject-Predicate-Object> for accurate Scene Graph Generation (SGG) is highly challenging due to the fluctuating spatio-temporal complexity. Inspired by the reasoning capabilities of Large Language Models (LLMs), we propose SceneLLM, a novel framework that leverages LLMs as powerful scene analyzers for dynamic SGG. Our framework introduces a Video-to-Language (V2L) mapping module that transforms video frames into linguistic signals (scene tokens), making the input more comprehensible for LLMs. To better encode spatial information, we devise a Spatial Information Aggregation (SIA) scheme, inspired by the structure of Chinese characters, which encodes spatial data into tokens. Using Optimal Transport (OT), we generate an implicit language signal from the frame-level token sequence that captures the video's spatio-temporal information. To further improve the LLM's ability to process this implicit linguistic input, we apply Low-Rank Adaptation (LoRA) to fine-tune the model. Finally, we use a transformer-based SGG predictor to decode the LLM's reasoning and predict semantic triplets. Our method achieves state-of-the-art results on the Action Genome (AG) benchmark, and extensive experiments show the effectiveness of SceneLLM in understanding and generating accurate dynamic scene graphs.

Related papers

• SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization [70.11167263638562]
  Social relation reasoning aims to identify relation categories such as friends, spouses, and colleagues from images. We first present a simple yet well-crafted framework named name, which combines the perception capability of Vision Foundation Models (VFMs) and the reasoning capability of Large Language Models (LLMs) within a modular framework.
  arXiv  Detail & Related papers  (2024-10-28T18:10:26Z)
• An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMs [7.630967411418269]
  Gloss-free Sign Language Translation (SLT) converts sign videos directly into spoken language sentences without relying on glosses. This paper emphasizes the importance of capturing the spatial configurations and motion dynamics inherent in sign language. We introduce Spatial and Motion-based Sign Language Translation (SpaMo), a novel LLM-based SLT framework.
  arXiv  Detail & Related papers  (2024-08-20T07:10:40Z)
• Aligning Actions and Walking to LLM-Generated Textual Descriptions [3.1049440318608568]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains. This work explores the use of LLMs to generate rich textual descriptions for motion sequences, encompassing both actions and walking patterns.
  arXiv  Detail & Related papers  (2024-04-18T13:56:03Z)
• ST-LLM: Large Language Models Are Effective Temporal Learners [58.79456373423189]
  Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation. How to effectively encode and understand videos in video-based dialogue systems remains to be solved. We propose ST-LLM, an effective video-LLM baseline with spatial-temporal sequence modeling inside LLM.
  arXiv  Detail & Related papers  (2024-03-30T10:11:26Z)
• Large Language Model with Graph Convolution for Recommendation [21.145230388035277]
  Text information can sometimes be of low quality, hindering its effectiveness for real-world applications. With knowledge and reasoning capabilities capsuled in Large Language Models, utilizing LLMs emerges as a promising way for description improvement. We propose a Graph-aware Convolutional LLM method to elicit LLMs to capture high-order relations in the user-item graph.
  arXiv  Detail & Related papers  (2024-02-14T00:04:33Z)
• VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding [63.075626670943116]
  We introduce a cutting-edge framework, VaQuitA, designed to refine the synergy between video and textual information. At the data level, instead of sampling frames uniformly, we implement a sampling method guided by CLIP-score rankings. At the feature level, we integrate a trainable Video Perceiver alongside a Visual-Query Transformer.
  arXiv  Detail & Related papers  (2023-12-04T19:48:02Z)
• CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding [66.52659447360104]
  CoVLM can guide the LLM to explicitly compose visual entities and relationships among the text. We propose CoVLM, which can guide the LLM to explicitly compose visual entities and relationships among the text.
  arXiv  Detail & Related papers  (2023-11-06T18:59:44Z)
• LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision [44.13777026011408]
  We learn semantic properties that capture rich spatial and temporal in video data by leveraging high-level logic specifications. We evaluate our method on three datasets with rich spatial representations and temporal specifications: 20BN-Something-GEN, MUGEN, and OpenPVSG.
  arXiv  Detail & Related papers  (2023-04-15T22:24:05Z)
• 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)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)

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.