Related papers: $\text{PKS}^4$:Parallel Kinematic Selective State …
Segment Anything Model (SAM) exhibits remarkable zero-shot segmentation capability; however, its prohibitive computational costs make edge deployment challenging. Although post-training quantization (PTQ) offers a promising compression…
A primary challenge faced in few-shot action recognition is inadequate video data for training. To address this issue, current methods in this field mainly focus on devising algorithms at the feature level while little attention is paid to…
Multimodal large language models (MLLMs) have enabled open-world visual understanding by injecting visual input as extra tokens into large language models (LLMs) as contexts. However, when the visual input changes from a single image to a…
Deep State Space Models (SSMs), such as Mamba (Gu & Dao, 2024), have become powerful tools for language modeling, offering high performance and linear scalability with sequence length. However, the application of parameter-efficient…
State Space Models (SSMs) have emerged as powerful architectures in computer vision, yet improving their computational efficiency remains crucial for practical and scalable deployment.While token reduction serves as an effective approach…
Video large language models (LLMs) achieve strong video understanding by leveraging a large number of spatio-temporal tokens, but suffer from quadratic computational scaling with token count. To address this, we propose a training-free…
State space models (SSMs) have gained attention by showing potential to outperform Transformers. However, previous studies have not sufficiently addressed the mechanisms underlying their high performance owing to a lack of theoretical…
State Space Models (SSMs) are powerful tools for modeling sequential data in computer vision and time series analysis domains. However, traditional SSMs are limited by fixed, one-dimensional sequential processing, which restricts their…
While modern best practices advocate for scalable architectures that support long-range interactions, object-centric models are yet to fully embrace these architectures. In particular, existing object-centric models for handling sequential…
Parameter-efficient fine-tuning (PEFT) aims to adapt pre-trained vision models to downstream tasks. Among PEFT paradigms, sparse tuning achieves remarkable performance by adjusting only the weights most relevant to downstream tasks, rather…
Two major challenges of 3D LiDAR Panoptic Segmentation (PS) are that point clouds of an object are surface-aggregated and thus hard to model the long-range dependency especially for large instances, and that objects are too close to…
In this paper, we present an efficient spatial-temporal representation for video person re-identification (reID). Firstly, we propose a Bilateral Complementary Network (BiCnet) for spatial complementarity modeling. Specifically, BiCnet…
Real-time video analysis remains a challenging problem in computer vision, requiring efficient processing of both spatial and temporal information while maintaining computational efficiency. Existing approaches often struggle to balance…
Vision Transformer models have shown impressive effectiveness in the surgical video understanding tasks through long-range dependency modeling. However, current methods suffer from prohibitive computational costs due to processing massive…
Autoregressive (AR) diffusion enables streaming, interactive long-video generation by producing frames causally, yet maintaining coherence over minute-scale horizons remains challenging due to accumulated errors, motion drift, and content…
Parameter-efficient fine-tuning (PEFT) is an effective method for adapting pre-trained vision models to downstream tasks by tuning a small subset of parameters. Among PEFT methods, sparse tuning achieves superior performance by only…
State space models (SSMs) achieve linear-time complexity but struggle with multi-channel physiological signals due to three limitations: fixed kernels cannot capture multi-scale temporal dynamics (motor preparation over hundreds of…
Instruction-guided generative models, especially those using text-to-image (T2I) and text-to-video (T2V) diffusion frameworks, have advanced the field of content editing in recent years. To extend these capabilities to 4D scene, we…
Point cloud videos can faithfully capture real-world spatial geometries and temporal dynamics, which are essential for enabling intelligent agents to understand the dynamically changing world. However, designing an effective 4D backbone…
Recent advances in inference-time scaling, particularly those leveraging reinforcement learning with verifiable rewards, have substantially enhanced the reasoning capabilities of Large Vision-Language Models (LVLMs). Inspired by this…