ViLLa: Video Reasoning Segmentation with Large Language Model

• URL: http://arxiv.org/abs/2407.14500v3
• Date: Sun, 16 Mar 2025 14:39:54 GMT
• Title: ViLLa: Video Reasoning Segmentation with Large Language Model
• Authors: Rongkun Zheng, Lu Qi, Xi Chen, Yi Wang, Kun Wang, Yu Qiao, Hengshuang Zhao,
• Abstract summary: We present ViLLa: Video reasoning segmentation with Large Language Model.<n>Our ViLLa manages to tackle these challenges through multiple core innovations.<n>To enable efficient processing of long videos, ViLLa incorporates (3) a key segment sampler that adaptively partitions long videos into shorter but semantically dense segments for less redundancy.
• Score: 48.75470418596875
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent efforts in video reasoning segmentation (VRS) integrate large language models (LLMs) with perception models to localize and track objects via textual instructions, achieving barely satisfactory results in simple scenarios. However, they struggled to discriminate and deduce the objects from user queries in more real-world scenes featured by long durations, multiple objects, rapid motion, and heavy occlusions. In this work, we analyze the underlying causes of these limitations, and present ViLLa: Video reasoning segmentation with Large Language Model. Remarkably, our ViLLa manages to tackle these challenges through multiple core innovations: (1) a context synthesizer that dynamically encodes the user intent with video contexts for accurate reasoning, resolving ambiguities in complex queries, and (2) a hierarchical temporal synchronizer that disentangles multi-object interactions across complex temporal scenarios by modelling multi-object interactions at local and global temporal scales. To enable efficient processing of long videos, ViLLa incorporates (3) a key segment sampler that adaptively partitions long videos into shorter but semantically dense segments for less redundancy. What's more, to promote research in this unexplored area, we construct a VRS benchmark, VideoReasonSeg, featuring different complex scenarios. Our model also exhibits impressive state-of-the-art results on VideoReasonSeg, Ref-YouTube-VOS, Ref-DAVIS17, MeViS, and ReVOS. Both quantitative and qualitative experiments demonstrate that our method effectively enhances video reasoning segmentation capabilities for multimodal LLMs. The code and dataset will be available at https://github.com/rkzheng99/ViLLa.

Related papers

• 4th PVUW MeViS 3rd Place Report: Sa2VA [105.88675577642204]
  We show that with a simple modification to the test time inference method on stronger MLLMs, we can lead to stronger results on MeVIS. In particular, we adopt the recent method Sa2VA, a unified model for dense grounded understanding of both images and videos.
  arXiv  Detail & Related papers  (2025-04-01T07:06:47Z)
• ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation [14.534308478766476]
  We introduce ViCaS, a new dataset containing thousands of challenging videos. Our benchmark evaluates models on holistic/high-level understanding and language-guided, pixel-precise segmentation.
  arXiv  Detail & Related papers  (2024-12-12T23:10:54Z)
• SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis [52.050036778325094]
  We introduce SALOVA: Segment-Augmented Video Assistant, a novel video-LLM framework designed to enhance the comprehension of lengthy video content. We present a high-quality collection of 87.8K long videos, each densely captioned at the segment level to enable models to capture scene continuity and maintain rich context. Our framework mitigates the limitations of current video-LMMs by allowing for precise identification and retrieval of relevant video segments in response to queries.
  arXiv  Detail & Related papers  (2024-11-25T08:04:47Z)
• One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos [41.34787907803329]
  VideoLISA is a video-based multimodal large language model designed to tackle the problem of language-instructed reasoning segmentation in videos. VideoLISA generates temporally consistent segmentation masks in videos based on language instructions.
  arXiv  Detail & Related papers  (2024-09-29T07:47:15Z)
• VISA: Reasoning Video Object Segmentation via Large Language Models [64.33167989521357]
  We introduce a new task, Reasoning Video Object (ReasonVOS) This task aims to generate a sequence of segmentation masks in response to implicit text queries that require complex reasoning abilities. We introduce VISA (Video-based large language Instructed Assistant) to tackle ReasonVOS.
  arXiv  Detail & Related papers  (2024-07-16T02:29:29Z)
• LongVLM: Efficient Long Video Understanding via Large Language Models [55.813206751150716]
  LongVLM is a simple yet powerful VideoLLM for long video understanding. We encode video representations that incorporate both local and global information. Our model produces more precise responses for long video understanding.
  arXiv  Detail & Related papers  (2024-04-04T11:33:29Z)
• TAM-VT: Transformation-Aware Multi-scale Video Transformer for Segmentation and Tracking [33.75267864844047]
  Video Object (VOS) has emerged as an increasingly important problem with availability of larger datasets and more complex and realistic settings. We propose a novel, clip-based DETR-style encoder-decoder architecture, which focuses on systematically analyzing and addressing aforementioned challenges. Specifically, we propose a novel transformation-aware loss that focuses learning on portions of the video where an object undergoes significant deformations.
  arXiv  Detail & Related papers  (2023-12-13T21:02:03Z)
• SPOT! Revisiting Video-Language Models for Event Understanding [31.49859545456809]
  We introduce SPOT Prober, to benchmark existing video-language models's capacities of distinguishing event-level discrepancies. We evaluate the existing video-language models with these positive and negative captions and find they fail to distinguish most of the manipulated events. Based on our findings, we propose to plug in these manipulated event captions as hard negative samples and find them effective in enhancing models for event understanding.
  arXiv  Detail & Related papers  (2023-11-21T18:43:07Z)
• Tracking Anything with Decoupled Video Segmentation [87.07258378407289]
  We develop a decoupled video segmentation approach (DEVA) It is composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks.
  arXiv  Detail & Related papers  (2023-09-07T17:59:41Z)
• MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions [93.35942025232943]
  We propose a large-scale dataset called MeViS, which contains numerous motion expressions to indicate target objects in complex environments. The goal of our benchmark is to provide a platform that enables the development of effective language-guided video segmentation algorithms.
  arXiv  Detail & Related papers  (2023-08-16T17:58:34Z)
• LISA: Reasoning Segmentation via Large Language Model [68.24075852136761]
  We propose a new segmentation task -- reasoning segmentation. The task is designed to output a segmentation mask given a complex and implicit query text. We present LISA: large Language Instructed Assistant, which inherits the language generation capabilities of multimodal Large Language Models.
  arXiv  Detail & Related papers  (2023-08-01T17:50:17Z)
• Segmenting Moving Objects via an Object-Centric Layered Representation [100.26138772664811]
  We introduce an object-centric segmentation model with a depth-ordered layer representation. We introduce a scalable pipeline for generating synthetic training data with multiple objects. We evaluate the model on standard video segmentation benchmarks.
  arXiv  Detail & Related papers  (2022-07-05T17:59:43Z)
• A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus [31.387948069111893]
  We show how to identify a short segment in a long video that semantically matches a text query. To tackle this problem, we propose the HierArchical Multi-Modal EncodeR (HAMMER) that encodes a video at both the coarse-grained clip level and the fine-trimmed frame level. We conduct extensive experiments to evaluate our model on moment localization in video corpus on ActivityNet Captions and TVR datasets.
  arXiv  Detail & Related papers  (2020-11-18T02:42:36Z)

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.