REVIEW 7 cited by
Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In this paper, we introduce a new sequence-to-sequence learning framework for RGB-based and multi-modal object tracking. First, we present SeqTrack for RGB-based tracking. It casts visual tracking as a sequence generation task, forecasting object bounding boxes in an autoregressive manner. This differs from previous trackers, which depend on the design of intricate head networks, such as classification and regression heads. SeqTrack employs a basic encoder-decoder transformer architecture. The encoder utilizes a bidirectional transformer for feature extraction, while the decoder generates bounding box sequences autoregressively using a causal transformer. The loss function is a plain cross-entropy. Second, we introduce SeqTrackv2, a unified sequence-to-sequence framework for multi-modal tracking tasks. Expanding upon SeqTrack, SeqTrackv2 integrates a unified interface for auxiliary modalities and a set of task-prompt tokens to specify the task. This enables it to manage multi-modal tracking tasks using a unified model and parameter set. This sequence learning paradigm not only simplifies the tracking framework, but also showcases superior performance across 14 challenging benchmarks spanning five single- and multi-modal tracking tasks. The code and models are available at https://github.com/chenxin-dlut/SeqTrackv2.
Forward citations
Cited by 7 Pith papers
-
Unified Multimodal Visual Tracking with Dual Mixture-of-Experts
OneTrackerV2 unifies multimodal tracking via Meta Merger and Dual Mixture-of-Experts to reach state-of-the-art results on five tasks and 12 benchmarks with efficiency and robustness when modalities are missing.
-
Models as Tools: An Agentic Coordination Framework for Unified Multimodal Visual Tracking
ACTrack coordinates a tracker, a segmentation model, and a VLM through event-triggered conflicts, reporting state-of-the-art RGB and multimodal tracking with 30% trainable parameters.
-
RELO: Reinforcement Learning to Localize for Visual Object Tracking
RELO replaces handcrafted spatial priors with a reinforcement learning policy for target localization in visual tracking and reports 57.5% AUC on LaSOText without template updates.
-
RELO: Reinforcement Learning to Localize for Visual Object Tracking
RELO formulates visual object tracking localization as a Markov decision process solved by reinforcement learning with combined IoU and AUC rewards, augmented by layer-aligned temporal token propagation, and reports 5...
-
Group Orthogonal Low-Rank Adaptation for RGB-T Tracking
GOLA reduces redundancy in low-rank adaptation for RGB-T tracking by using SVD-based partitioning and inter-group orthogonal constraints to enable complementary feature learning, outperforming prior methods on four be...
-
Decoupled Spatio-Temporal Consistency Learning for Self-Supervised Tracking
SSTrack trains a Vision Transformer tracker without frame-wise box labels by combining forward global search, backward local association, and instance contrastive learning, and reports state-of-the-art self-supervised...
-
Boosting Self-Supervised Tracking with Contextual Prompts and Noise Learning
A dual-stage self-supervised tracker learns robust representations by first using semantic prompts on forward and backward branches then injecting contextual noise to handle complex feature spaces.
Discussion (0). Sign in to comment.