Related papers: Hierarchical Temporal Context Learning for Camera-…

Continuous sign language recognition (cSLR) is a public significant task that transcribes a sign language video into an ordered gloss sequence. It is important to capture the fine-grained gloss-level details, since there is no explicit…

In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities. To overcome these challenges, we introduce a novel Visual…

Current techniques in Visual Simultaneous Localization and Mapping (VSLAM) estimate camera displacement by comparing image features of consecutive scenes. These algorithms depend on scene continuity, hence requires frequent camera inputs.…

Automated requirements assessment traditionally relies on universal patterns as proxies for defectiveness, implemented through rule-based heuristics or machine learning classifiers trained on large annotated datasets. However, what…

Conformal prediction (CP) is a powerful framework for quantifying uncertainty in machine learning models, offering reliable predictions with finite-sample coverage guarantees. When applied to classification, CP produces a prediction set of…

Anomaly identification is highly dependent on the relationship between the object and the scene, as different/same object actions in same/different scenes may lead to various degrees of normality and anomaly. Therefore, object-scene…

Existing self-supervised learning (SSL) methods primarily learn object-invariant representations but often neglect the spatial structure and relationships among object parts. To address this limitation, we introduce Spatial Prediction (SP),…

Vision-language models like CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions because of their training focus on short and concise captions. We present…

We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. This meta-training…

We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D scan of a scene as input and predicting a complete 3D model along with per-voxel semantic labels. The key contribution of our method is its ability to…

Spatio-Temporal predictive Learning is a self-supervised learning paradigm that enables models to identify spatial and temporal patterns by predicting future frames based on past frames. Traditional methods, which use recurrent neural…

Subspace learning (SL) plays an important role in hyperspectral image (HSI) classification, since it can provide an effective solution to reduce the redundant information in the image pixels of HSIs. Previous works about SL aim to improve…

Vision-language models such as CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions due to pre-training on short and concise captions. We present FAST-GOAL…

Sequential matching using hand-crafted heuristics has been standard practice in route-based place recognition for enhancing pairwise similarity results for nearly a decade. However, precision-recall performance of these algorithms…

Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latency and high dynamic range, capture brightness changes asynchronously, offering a unique…

3D scene understanding is fundamental for embodied AI and robotics, supporting reliable perception for interaction and navigation. Recent approaches achieve zero-shot, open-vocabulary 3D semantic mapping by assigning embedding vectors to 2D…

Whilst contrastive learning has recently brought notable benefits to deep clustering of unlabelled images by learning sample-specific discriminative visual features, its potential for explicitly inferring class decision boundaries is less…

State-of-the-art two-stage object detectors apply a classifier to a sparse set of object proposals, relying on region-wise features extracted by RoIPool or RoIAlign as inputs. The region-wise features, in spite of aligning well with the…

Semantic Scene Completion (SSC) aims to jointly generate space occupancies and semantic labels for complex 3D scenes. Most existing SSC models focus on volumetric representations, which are memory-inefficient for large outdoor spaces. Point…

Robotic manipulation tasks, such as object rearrangement, play a crucial role in enabling robots to interact with complex and arbitrary environments. Existing work focuses primarily on single-level rearrangement planning and, even if…