Related papers: SPMTrack: Spatio-Temporal Parameter-Efficient Fine…

This paper tackles the critical challenge of optimizing multi-modality trackers by effectively adapting pre-trained models for RGB data. Existing fine-tuning paradigms oscillate between excessive flexibility and over-restriction, both…

Achieving high-performance in multi-object tracking algorithms heavily relies on modeling spatio-temporal relationships during the data association stage. Mainstream approaches encompass rule-based and deep learning-based methods for…

Linear mixed-effects model (LMM) is a cornerstone of longitudinal data analysis, but is limited to adeptly make heterogeneous analyses predictable under both group-specific fixed effects and subject-specific random effects. To address this…

Sparse Mixture of Experts (SMoEs) models scale the capacity of models while maintaining constant computational overhead. Early designs typically relied on a fixed value of $k$, where $k$ represents either the number of experts selected per…

In online multi-target tracking, modeling of appearance and geometric similarities between pedestrians visual scenes is of great importance. The higher dimension of inherent information in the appearance model compared to the geometric…

Multi-Object Tracking (MOT) is a critical problem in computer vision, essential for understanding how objects move and interact in videos. This field faces significant challenges such as occlusions and complex environmental dynamics,…

Multimodal Visual Object Tracking (VOT) has recently gained significant attention due to its robustness. Early research focused on fully fine-tuning RGB-based trackers, which was inefficient and lacked generalized representation due to the…

Tracking small, agile multi-objects (SMOT), such as birds, from an Unmanned Aerial Vehicle (UAV) perspective is a highly challenging computer vision task. The difficulty stems from three main sources: the extreme scarcity of target…

We propose Tensor-Trained Low-Rank Adaptation Mixture of Experts (TT-LoRA MoE), a novel computational framework integrating Parameter-Efficient Fine-Tuning (PEFT) with sparse MoE routing to address scalability challenges in large model…

Real-world model deployment across multiple domains requires multimodal models to operate under two complementary regimes: (1) multi-task pretraining, tasks are co-available at design time where related tasks could borrow representational…

The success of visual tracking has been largely driven by datasets with manual box annotations. However, these box annotations require tremendous human effort, limiting the scale and diversity of existing tracking datasets. In this work, we…

Semi-supervised learning has been employed to alleviate the need for extensive labeled data for histopathology image segmentation, but existing methods struggle with noisy pseudo-labels due to ambiguous gland boundaries and morphological…

Spatial-temporal data modeling aims to mine the underlying spatial relationships and temporal dependencies of objects in a system. However, most existing methods focus on the modeling of spatial-temporal data in a single mode, lacking the…

Visual object tracking acts as a pivotal component in various emerging video applications. Despite the numerous developments in visual tracking, existing deep trackers are still likely to fail when tracking against objects with dramatic…

In this paper, we provide an intuitive viewing to simplify the Siamese-based trackers by converting the tracking task to a classification. Under this viewing, we perform an in-depth analysis for them through visual simulations and real…

Multi-Target Multi-Camera Tracking (MTMCT) has broad applications and forms the basis for numerous future city-wide systems (e.g. traffic management, crash detection, etc.). However, the challenge of matching vehicle trajectories across…

We present Sparse Interpolated Mixture-of-Experts (SIMoE) instruction-tuning, an end-to-end algorithm designed to fine-tune a dense pre-trained Large Language Model (LLM) into a MoE-style model that possesses capabilities in multiple…

We propose a novel few-shot action recognition framework, STRM, which enhances class-specific feature discriminability while simultaneously learning higher-order temporal representations. The focus of our approach is a novel spatio-temporal…

We present PSEUDo, an adaptive feature learning technique for exploring visual patterns in multi-track sequential data. Our approach is designed with the primary focus to overcome the uneconomic retraining requirements and inflexible…

Large Multimodal Models (LMMs) have recently gained prominence in autonomous driving research, showcasing promising capabilities across various emerging benchmarks. LMMs specifically designed for this domain have demonstrated effective…