Related papers: Context Guided Transformer Entropy Modeling for Vi…
Vision-Language Models (VLMs) such as CLIP enable strong zero-shot recognition but suffer substantial degradation under distribution shifts. Test-Time Adaptation (TTA) aims to improve robustness using only unlabeled test samples, yet most…
3D convolution neural networks (CNNs) have been the prevailing option for video recognition. To capture the temporal information, 3D convolutions are computed along the sequences, leading to cubically growing and expensive computations. To…
Recent work on Vision Transformers (VTs) showed that introducing a local inductive bias in the VT architecture helps reducing the number of samples necessary for training. However, the architecture modifications lead to a loss of generality…
In an intelligent transportation system, the key problem of traffic forecasting is how to extract periodic temporal dependencies and complex spatial correlations. Current state-of-the-art methods for predicting traffic flow are based on…
As the basic building block of Convolutional Neural Networks (CNNs), the convolutional layer is designed to extract local patterns and lacks the ability to model global context in its nature. Many efforts have been recently devoted to…
In video analysis, understanding the temporal context is crucial for recognizing object interactions, event patterns, and contextual changes over time. The proposed model leverages adjacency and semantic similarities between objects from…
For learned image compression, the autoregressive context model is proved effective in improving the rate-distortion (RD) performance. Because it helps remove spatial redundancies among latent representations. However, the decoding process…
Text classification aims to assign labels to textual units by making use of global information. Recent studies have applied graph neural network (GNN) to capture the global word co-occurrence in a corpus. Existing approaches require that…
Grasp detection in a cluttered environment is still a great challenge for robots. Currently, the Transformer mechanism has been successfully applied to visual tasks, and its excellent ability of global context information extraction…
We propose ContextLM, a framework that implicitly learns multi-token prediction by augmenting standard pretraining with an intrinsic next-context prediction objective. ContextLM builds a language model on top of context embeddings that span…
When deploying artificial agents in real-world environments where they interact with humans, it is crucial that their behavior is aligned with the values, social norms or other requirements of that environment. However, many environments…
Semantic maps are increasingly utilized in areas such as robotics, autonomous systems, and extended reality, motivating the investigation of efficient compression methods that preserve structured semantic information. This paper studies…
In this paper, we re-examine the task of cross-modal clip-sentence retrieval, where the clip is part of a longer untrimmed video. When the clip is short or visually ambiguous, knowledge of its local temporal context (i.e. surrounding video…
Accurately predicting smartphone app usage is challenging due to the sparsity and irregularity of user behavior, especially under cold-start and low-activity conditions. Existing approaches mostly rely on static or attention-only…
Spatio-temporal video grounding (or STVG) task aims at locating a spatio-temporal tube for a specific instance given a text query. Despite advancements, current methods easily suffer the distractors or heavy object appearance variations in…
We describe a new semantic parsing setting that allows users to query the system using both natural language questions and actions within a graphical user interface. Multiple time series belonging to an entity of interest are stored in a…
Human activity intensity prediction is crucial to many location-based services. Despite tremendous progress in modeling dynamics of human activity, most existing methods overlook physical constraints of spatial interaction, leading to…
Recently, deep learning methods have shown promising results in point cloud compression. For octree-based point cloud compression, previous works show that the information of ancestor nodes and sibling nodes are equally important for…
Test-time adaptation aims to adapt to realistic environments in an online manner by learning during test time. Entropy minimization has emerged as a principal strategy for test-time adaptation due to its efficiency and adaptability.…
Test-time adaptation (TTA) aims at adapting a model pre-trained on the labeled source domain to the unlabeled target domain. Existing methods usually focus on improving TTA performance under covariate shifts, while neglecting semantic…