相关论文: OccamVTS: Distilling Vision Models to 1% Parameter…

Dataset distillation methods reduce large-scale datasets to smaller sets of synthetic data, preserving sufficient information to quickly train a new model from scratch. However, prior work on dataset distillation has focused exclusively on…

Machine learning methods trained on raw numerical time series data exhibit fundamental limitations such as a high sensitivity to the hyper parameters and even to the initialization of random weights. A combination of a recurrent neural…

Vision-language models (VLMs) have shown impressive zero- and few-shot performance on real-world visual question answering (VQA) benchmarks, alluding to their capabilities as visual reasoning engines. However, the benchmarks being used…

Time series forecasting is essential for agents to make decisions. Traditional approaches rely on statistical methods to forecast given past numeric values. In practice, end-users often rely on visualizations such as charts and plots to…

Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scenes evolve under egocentric motion. Recent efforts address…

While feature-based knowledge distillation has proven highly effective for compressing CNNs, these techniques unexpectedly fail when applied to Vision Transformers (ViTs), often performing worse than simple logit-based distillation. We…

Image denoising is essential in low-level vision applications such as photography and automated driving. Existing methods struggle with distinguishing complex noise patterns in real-world scenes and consume significant computational…

Autonomous driving gained huge traction in recent years, due to its potential to change the way we commute. Much effort has been put into trying to estimate the state of a vehicle. Meanwhile, learning to forecast the state of a vehicle…

Token pruning is essential for enhancing the computational efficiency of vision-language models (VLMs), particularly for video-based tasks where temporal redundancy is prevalent. Prior approaches typically prune tokens either (1) within the…

Irregularly sampled time series are increasingly prevalent, particularly in medical domains. While various specialized methods have been developed to handle these irregularities, effectively modeling their complex dynamics and pronounced…

Since the wide employment of deep learning frameworks in video salient object detection, the accuracy of the recent approaches has made stunning progress. These approaches mainly adopt the sequential modules, based on optical flow or…

To address the complexity of financial time series, this paper proposes a forecasting model combining sliding window and variational mode decomposition (VMD) methods. Historical stock prices and relevant market indicators are used to…

We introduce the first zero-shot approach for Video Semantic Segmentation (VSS) based on pre-trained diffusion models. A growing research direction attempts to employ diffusion models to perform downstream vision tasks by exploiting their…

Adapting visual programming or prompting large language models (LLMs) to generate executable code for visual tasks like visual question answering (VQA) for specialized tasks or domains remains challenging due to high annotation and…

Current state-of-the-art video quality models, such as VMAF, give excellent prediction results by comparing the degraded video with its reference video. However, they do not consider temporal distortions (e.g., frame freezes or skips) that…

Knowledge distillation from pretrained visual representation models offers an effective approach to improve small, task-specific production models. However, the effectiveness of such knowledge transfer drops significantly when distilling…

When people query Vision-Language Models (VLMs) but cannot see the accompanying visual context (e.g. for blind and low-vision users), augmenting VLM predictions with natural language explanations can signal which model predictions are…

Time series forecasting is an important yet challenging task. Though deep learning methods have recently been developed to give superior forecasting results, it is crucial to improve the interpretability of time series models. Previous…

Temporal Action Segmentation (TAS) requires dividing videos into action segments, yet the vast space of activities and alternative breakdowns makes collecting comprehensive datasets infeasible. Existing methods remain limited to closed…

While Vision-Language Models (VLMs) have achieved competitive performance in various tasks, their comprehension of the underlying structure and semantics of a scene remains understudied. To investigate the understanding of VLMs, we study…