Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation

• URL: http://arxiv.org/abs/2410.13437v1
• Date: Thu, 17 Oct 2024 11:07:05 GMT
• Title: Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation
• Authors: Changcheng Xiao, Qiong Cao, Yujie Zhong, Xiang Zhang, Tao Wang, Canqun Yang, Long Lan,
• Abstract summary: Referring multi-object tracking (RMOT) is an emerging cross-modal task that aims to locate an arbitrary number of target objects in a video. We introduce a compact Transformer-based method, termed TenRMOT, to exploit the advantages of Transformer architecture. TenRMOT demonstrates superior performance on both the referring multi-object tracking and the segmentation tasks.
• Score: 28.16053631036079
• License:
• Abstract: Referring multi-object tracking (RMOT) is an emerging cross-modal task that aims to locate an arbitrary number of target objects and maintain their identities referred by a language expression in a video. This intricate task involves the reasoning of linguistic and visual modalities, along with the temporal association of target objects. However, the seminal work employs only loose feature fusion and overlooks the utilization of long-term information on tracked objects. In this study, we introduce a compact Transformer-based method, termed TenRMOT. We conduct feature fusion at both encoding and decoding stages to fully exploit the advantages of Transformer architecture. Specifically, we incrementally perform cross-modal fusion layer-by-layer during the encoding phase. In the decoding phase, we utilize language-guided queries to probe memory features for accurate prediction of the desired objects. Moreover, we introduce a query update module that explicitly leverages temporal prior information of the tracked objects to enhance the consistency of their trajectories. In addition, we introduce a novel task called Referring Multi-Object Tracking and Segmentation (RMOTS) and construct a new dataset named Ref-KITTI Segmentation. Our dataset consists of 18 videos with 818 expressions, and each expression averages 10.7 masks, which poses a greater challenge compared to the typical single mask in most existing referring video segmentation datasets. TenRMOT demonstrates superior performance on both the referring multi-object tracking and the segmentation tasks.

Related papers

• MLS-Track: Multilevel Semantic Interaction in RMOT [31.153018571396206]
  We propose a high-quality yet low-cost data generation method base on Unreal Engine 5. We construct a brand-new benchmark dataset, named Refer-UE-City, which primarily includes scenes from intersection surveillance videos. We also propose a multi-level semantic-guided multi-object framework called MLS-Track, where the interaction between the model and text is enhanced layer by layer.
  arXiv  Detail & Related papers  (2024-04-18T09:31:03Z)
• DOCTR: Disentangled Object-Centric Transformer for Point Scene Understanding [7.470587868134298]
  Point scene understanding is a challenging task to process real-world scene point cloud. Recent state-of-the-art method first segments each object and then processes them independently with multiple stages for the different sub-tasks. We propose a novel Disentangled Object-Centric TRansformer (DOCTR) that explores object-centric representation.
  arXiv  Detail & Related papers  (2024-03-25T05:22:34Z)
• Referring Multi-Object Tracking [78.63827591797124]
  We propose a new and general referring understanding task, termed referring multi-object tracking (RMOT) Its core idea is to employ a language expression as a semantic cue to guide the prediction of multi-object tracking. To the best of our knowledge, it is the first work to achieve an arbitrary number of referent object predictions in videos.
  arXiv  Detail & Related papers  (2023-03-06T18:50:06Z)
• Position-Aware Contrastive Alignment for Referring Image Segmentation [65.16214741785633]
  We present a position-aware contrastive alignment network (PCAN) to enhance the alignment of multi-modal features. Our PCAN consists of two modules: 1) Position Aware Module (PAM), which provides position information of all objects related to natural language descriptions, and 2) Contrastive Language Understanding Module (CLUM), which enhances multi-modal alignment.
  arXiv  Detail & Related papers  (2022-12-27T09:13:19Z)
• End-to-end Tracking with a Multi-query Transformer [96.13468602635082]
  Multiple-object tracking (MOT) is a challenging task that requires simultaneous reasoning about location, appearance, and identity of the objects in the scene over time. Our aim in this paper is to move beyond tracking-by-detection approaches, to class-agnostic tracking that performs well also for unknown object classes.
  arXiv  Detail & Related papers  (2022-10-26T10:19:37Z)
• 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)
• MeMOT: Multi-Object Tracking with Memory [97.48960039220823]
  Our model, called MeMOT, consists of three main modules that are all Transformer-based. MeMOT observes very competitive performance on widely adopted MOT datasets.
  arXiv  Detail & Related papers  (2022-03-31T02:33:20Z)
• Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation [95.74244714914052]
  Multiple object tracking and segmentation requires detecting, tracking, and segmenting objects belonging to a set of given classes. We propose Prototypical Cross-Attention Network (PCAN), capable of leveraging rich-temporal information online. PCAN outperforms current video instance tracking and segmentation competition winners on Youtube-VIS and BDD100K datasets.
  arXiv  Detail & Related papers  (2021-06-22T17:57:24Z)
• Spatio-Temporal Multi-Task Learning Transformer for Joint Moving Object Detection and Segmentation [0.0]
  We present a Multi-Task Learning architecture, based on Transformers, to jointly perform both tasks through one network. We evaluate the performance of the individual tasks architecture versus the MTL setup, both with early shared encoders, and late shared encoder-decoder transformers.
  arXiv  Detail & Related papers  (2021-06-21T20:30:44Z)
• Revisiting Sequence-to-Sequence Video Object Segmentation with Multi-Task Loss and Skip-Memory [4.343892430915579]
  Video Object (VOS) is an active research area of the visual domain. Current approaches lose objects in longer sequences, especially when the object is small or briefly occluded. We build upon a sequence-to-sequence approach that employs an encoder-decoder architecture together with a memory module for exploiting the sequential data.
  arXiv  Detail & Related papers  (2020-04-25T15:38:09Z)

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.