7 accepted papers
Accurate 3D scene description is fundamental to robotic navigation and augmented reality, yet current dense captioning methods face significant limitations in processing sparse point cloud data.Existing approaches that apply Euclidean embedding spaces struggle to simultaneously preserve fine-grained
Although Federated Fine-Tuning (FFT) facilitates the fine-tuning of Large Language Models (LLMs) across data owners without compromising their privacy, it suffers from severe communication overheads caused by numerous parameters of LLMs even with Parameter-Efficient Fine-Tuning (PEFT) methods. To ad…
Face Forgery Video Detection (FFVD) is a critical yet challenging task in determining whether a digital facial video is authentic or forged. Existing FFVD methods typically focus on isolated spatial or coarsely fused spatiotemporal information, failing to leverage temporal forgery cues thus resultin…
Group Equivariant Convolution (GConv) empowers models to explore underlying symmetry in data, improving performance. However, real-world scenarios often deviate from ideal symmetric systems caused by physical permutation, characterized by non-trivial actions of a symmetry group, resulting in asymmet…
Group Equivariant Convolution (GConv) can capture rotational equivariance from original data. It assumes uniform and strict rotational equivariance across all features as the transformations under the specific group. However, the presentation or distribution of real-world data rarely conforms to str…
Human trajectory prediction is crucial in human-computer interaction and even in the safety of autonomous driving. In this work, A new method, called Social Latent Ordinary Differential Equation (Social LODE), is introduced for predicting human trajectories. The backbone of Social LODE consists of a…
Recently, the attention mechanism has shown outstanding competence in capturing global structure information and long-range relationships within data, thus enhancing the performance of deep vision models on various computer vision tasks. In this work, we propose a novel dictionary learning-based att…