Related papers: STaRFormer: Semi-Supervised Task-Informed Represen…
User interests are usually dynamic in the real world, which poses both theoretical and practical challenges for learning accurate preferences from rich behavior data. Among existing user behavior modeling solutions, attention networks are…
Recently, transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. Specifically, object queries are guided by the initial instance masks in the first cross-attention, and then iteratively…
Sequential modelling of high-dimensional data is an important problem that appears in many domains including model-based reinforcement learning and dynamics identification for control. Latent variable models applied to sequential data…
Panoptic segmentation involves a combination of joint semantic segmentation and instance segmentation, where image contents are divided into two types: things and stuff. We present Panoptic SegFormer, a general framework for panoptic…
DAVIS camera, streaming two complementary sensing modalities of asynchronous events and frames, has gradually been used to address major object detection challenges (e.g., fast motion blur and low-light). However, how to effectively…
Remote sensing change detection aims to compare two or more images recorded for the same area but taken at different time stamps to quantitatively and qualitatively assess changes in geographical entities and environmental factors.…
Transformers have emerged as a powerful tool for a broad range of natural language processing tasks. A key component that drives the impressive performance of Transformers is the self-attention mechanism that encodes the influence or…
Capitalizing on large pre-trained models for various downstream tasks of interest have recently emerged with promising performance. Due to the ever-growing model size, the standard full fine-tuning based task adaptation strategy becomes…
Supervised learning in large discriminative models is a mainstay for modern computer vision. Such an approach necessitates investing in large-scale human-annotated datasets for achieving state-of-the-art results. In turn, the efficacy of…
Domain-generalized urban-scene semantic segmentation (USSS) aims to learn generalized semantic predictions across diverse urban-scene styles. Unlike domain gap challenges, USSS is unique in that the semantic categories are often similar in…
Most existing methods realize 3D instance segmentation by extending those models used for 3D object detection or 3D semantic segmentation. However, these non-straightforward methods suffer from two drawbacks: 1) Imprecise bounding boxes or…
Recent advancements in multimodal large models have significantly bridged the representation gap between diverse modalities, catalyzing the evolution of video multimodal interpretation, which enhances users' understanding of video content…
Scene Text Recognition (STR), the task of recognizing text against complex image backgrounds, is an active area of research. Current state-of-the-art (SOTA) methods still struggle to recognize text written in arbitrary shapes. In this…
Spatial transcriptomics (ST) enables transcriptome-wide profiling while preserving the spatial context of tissues, offering unprecedented opportunities to study tissue organization and cell-cell interactions in situ. Despite recent…
Human Activity Recognition (HAR) using wearable sensor data has become a central task in mobile computing, healthcare, and human-computer interaction. Despite the success of traditional deep learning models such as CNNs and RNNs, they often…
The perception of moving objects is crucial for autonomous robots performing collision avoidance in dynamic environments. LiDARs and cameras tremendously enhance scene interpretation but do not provide direct motion information and face…
Accurate prediction of driving intention is key to enhancing the safety and interactive efficiency of human-machine co-driving systems. It serves as a cornerstone for achieving high-level autonomous driving. However, current approaches…
As acquiring pixel-wise annotations of real-world images for semantic segmentation is a costly process, a model can instead be trained with more accessible synthetic data and adapted to real images without requiring their annotations. This…
Aggregating multi-modality data to obtain reliable data representation attracts more and more attention. Recent studies demonstrate that Transformer models usually work well for multi-modality tasks. Existing Transformers generally either…
Instance segmentation is essential for applications such as automated monitoring of plant health, growth, and yield. However, extensive effort is required to create large-scale datasets with pixel-level annotations of each object instance…