Related papers: Uncertainty-Guided Inference-Time Depth Adaptation…

Robust and adaptive control strategies are needed when robots or automated systems are introduced to unknown and dynamic environments where they are required to cope with disturbances, unmodeled dynamics, and parametric uncertainties. In…

Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a…

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

Previous works have attempted to improve tracking efficiency through lightweight architecture design or knowledge distillation from teacher models to compact student trackers. However, these solutions often sacrifice accuracy for speed to a…

DEtection TRansformer (DETR) for object detection reaches competitive performance compared with Faster R-CNN via a transformer encoder-decoder architecture. However, trained with scratch transformers, DETR needs large-scale training data…

Despite advances in generic object detection, there remains a performance gap in detecting small objects compared to normal-scale objects. We reveal that conventional object localization methods suffer from gradient instability in small…

Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on…

Computational imaging plays a pivotal role in determining hidden information from sparse measurements. A robust inverse solver is crucial to fully characterize the uncertainty induced by these measurements, as it allows for the estimation…

Existing deep trackers are typically trained with largescale video frames with annotated bounding boxes. However, these bounding boxes are expensive and time-consuming to annotate, in particular for large scale datasets. In this paper, we…

Graph Neural Networks (GNNs) have become a prominent approach for learning from graph-structured data. However, their effectiveness can be significantly compromised when the graph structure is suboptimal. To address this issue, Graph…

Weakly Supervised Object Localization (WSOL), which aims to localize objects by only using image-level labels, has attracted much attention because of its low annotation cost in real applications. Recent studies leverage the advantage of…

Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which…

Localization is a fundamental task in robotics for autonomous navigation. Existing localization methods rely on a single input data modality or train several computational models to process different modalities. This leads to stringent…

We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a…

Video saliency prediction and detection are thriving research domains that enable computers to simulate the distribution of visual attention akin to how humans perceiving dynamic scenes. While many approaches have crafted task-specific…

High-resolution geometric prediction is essential for robust perception in autonomous driving, robotics, and AR/MR, but current foundation models are fundamentally limited by their scalability to real-world, high-resolution scenarios.…

Existing tracking algorithms typically rely on low-frame-rate RGB cameras coupled with computationally intensive deep neural network architectures to achieve effective tracking. However, such frame-based methods inherently face challenges…

Accurate observation of dynamic environments traditionally relies on synthesizing raw, signal-level information from multiple distributed sensors. This work investigates an alternative approach: performing geospatial inference using only…

In this study, we address the key challenges concerning the accuracy and effectiveness of depth estimation for endoscopic imaging, with a particular emphasis on real-time inference and the impact of light reflections. We propose a novel…

In this paper, we propose a novel query design for the transformer-based object detection. In previous transformer-based detectors, the object queries are a set of learned embeddings. However, each learned embedding does not have an…