2 citations · 6 across the 16 of their papers we have counts for
16 papers · 1 filter
Weave Forcing: Compositional Memory Routing for Interactive Long Video Generation
Ziyi Wang, Junchi Yao, Heqian Qiu +5
Recent advances in autoregressive video generation have improved temporal consistency over extended durations, yet interactive storytelling requires more than continuous scene exte…
Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting
Zhaofeng Shi, Heqian Qiu, Lanxiao Wang +2
Perceiving multimodal cues and forecasting fine-grained actions from an egocentric (Ego) perspective is vital for applications like robot manipulation. However, previous studies ei…
Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency
Zhaofeng Shi, Heqian Qiu, Lanxiao Wang +4
Efficient adaptation between Egocentric (Ego) and Exocentric (Exo) views is crucial for applications such as human-robot cooperation. However, the success of most existing Ego-Exo…
SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusion
Xiang Li, Heqian Qiu, Lanxiao Wang +4
Error detection is crucial in industrial training, healthcare, and assembly quality control. Most existing work assumes a single-view setting and cannot handle the practical case w…
Attention-disentangled Uniform Orthogonal Feature Space Optimization for Few-shot Object Detection
Taijin Zhao, Heqian Qiu, Yu Dai +4
Few-shot object detection (FSOD) aims to detect objects with limited samples for novel classes, while relying on abundant data for base classes. Existing FSOD approaches, predomina…
Challenges and Trends in Egocentric Vision: A Survey
Xiang Li, Heqian Qiu, Lanxiao Wang +5
With the rapid development of artificial intelligence technologies and wearable devices, egocentric vision understanding has emerged as a new and challenging research direction, gr…
EgoMe: A New Dataset and Challenge for Following Me via Egocentric View in Real World
Heqian Qiu, Zhaofeng Shi, Lanxiao Wang +3
In human imitation learning, the imitator typically take the egocentric view as a benchmark, naturally transferring behaviors observed from an exocentric view to their owns, which…
Modulating CNN Features with Pre-Trained ViT Representations for Open-Vocabulary Object Detection
Xiangyu Gao, Yu Dai, Benliu Qiu +3
Owing to large-scale image-text contrastive training, pre-trained vision language model (VLM) like CLIP shows superior open-vocabulary recognition ability. Most existing open-vocab…
ARIC: An Activity Recognition Dataset in Classroom Surveillance Images
Linfeng Xu, Fanman Meng, Qingbo Wu +16
The application of activity recognition in the ``AI + Education" field is gaining increasing attention. However, current work mainly focuses on the recognition of activities in man…
Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation
Zhaofeng Shi, Heqian Qiu, Lanxiao Wang +3
In this paper, we explore a novel Text-supervised Egocentic Semantic Segmentation (TESS) task that aims to assign pixel-level categories to egocentric images weakly supervised by t…
Region Prompt Tuning: Fine-grained Scene Text Detection Utilizing Region Text Prompt
Xingtao Lin, Heqian Qiu, Lanxiao Wang +3
Recent advancements in prompt tuning have successfully adapted large-scale models like Contrastive Language-Image Pre-trained (CLIP) for downstream tasks such as scene text detecti…
Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning
Jian Jiao, Yu Dai, Hefei Mei +5
Recent video class-incremental learning usually excessively pursues the accuracy of the newly seen classes and relies on memory sets to mitigate catastrophic forgetting of the old…
MCF-VC: Mitigate Catastrophic Forgetting in Class-Incremental Learning for Multimodal Video Captioning
Huiyu Xiong, Lanxiao Wang, Heqian Qiu +3
To address the problem of catastrophic forgetting due to the invisibility of old categories in sequential input, existing work based on relatively simple categorization tasks has m…
GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detection
Hefei Mei, Taijin Zhao, Shiyuan Tang +5
Few-shot object detection (FSOD) aims to achieve object detection only using a few novel class training data. Most of the existing methods usually adopt a transfer-learning strateg…
Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond
Chen Shuai, Meng Fanman, Zhang Runtong +4
Few-shot segmentation (FSS) aims to segment the novel classes with a few annotated images. Due to CLIP's advantages of aligning visual and textual information, the integration of C…
RefCrowd: Grounding the Target in Crowd with Referring Expressions
Heqian Qiu, Hongliang Li, Taijin Zhao +3
Crowd understanding has aroused the widespread interest in vision domain due to its important practical significance. Unfortunately, there is no effort to explore crowd understandi…