Jae-pil Heo

Intrinsic Temporal Adaptation of CLIP for Partially Relevant Video Retrieval

Hyun Seok Seong, Woojin Jun, SuBeen Lee +1

Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos that contain moments relevant to a text query. Since the target moment occupies only a portion of the vi…

Selective Synergistic Learning for Video Object-Centric Learning

WonJun Moon, Jae-Pil Heo

Typical video object-centric learning (VOCL) approaches employ slot-based frameworks that rely on reconstruction-driven encoder-decoder architectures, where learning is mediated by…

Temporally Consistent Long-Term Memory for 3D Single Object Tracking

Jaejoon Yoo, SuBeen Lee, Yerim Jeon +2

3D Single Object Tracking (3D-SOT) aims to localize a target object across a sequence of LiDAR point clouds, given its 3D bounding box in the first frame. Recent methods have adopt…

Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation

ByeongCheol Lee, Hyun Seok Seong, Sangeek Hyun +3

A sliding-window inference strategy is commonly adopted in recent training-free open-vocabulary semantic segmentation methods to overcome limitation of the CLIP in processing high-…

Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning

WonJun Moon, Hyun Seok Seong, Jae-Pil Heo

Video Object-Centric Learning seeks to decompose raw videos into a small set of object slots, but existing slot-attention models often suffer from severe over-fragmentation. This i…

From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning

Hyun Seok Seong, WonJun Moon, Jae-Pil Heo

Unsupervised object-centric learning models, particularly slot-based architectures, have shown great promise in decomposing complex scenes. However, their reliance on reconstructio…

Auxiliary Descriptive Knowledge for Few-Shot Adaptation of Vision-Language Model

SuBeen Lee, GilHan Park, WonJun Moon +2

Despite the impressive zero-shot capabilities of Vision-Language Models (VLMs), they often struggle in downstream tasks with distribution shifts from the pre-training data. Few-Sho…

Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding

Yerim Jeon, Miso Lee, WonJun Moon +1

Recent advances in 3D scene-language understanding have leveraged Large Language Models (LLMs) for 3D reasoning by transferring their general reasoning ability to 3D multi-modal co…

White Aggregation and Restoration for Few-shot 3D Point Cloud Semantic Segmentation

Jiyun Im, SuBeen Lee, Miso Lee +1

Few-shot 3D Point Cloud Semantic Segmentation (FS-PCS) aims to predict per-point labels for an unlabeled point cloud, given only a few labeled examples. To extract representations…

Selective Contrastive Learning for Weakly Supervised Affordance Grounding

WonJun Moon, Hyun Seok Seong, Jae-Pil Heo

Facilitating an entity's interaction with objects requires accurately identifying parts that afford specific actions. Weakly supervised affordance grounding (WSAG) seeks to imitate…

Temporal Alignment-Free Video Matching for Few-shot Action Recognition

SuBeen Lee, WonJun Moon, Hyun Seok Seong +1

Few-Shot Action Recognition (FSAR) aims to train a model with only a few labeled video instances. A key challenge in FSAR is handling divergent narrative trajectories for precise v…

Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation

Suho Park, SuBeen Lee, Hyun Seok Seong +2

We propose Foreground-Covering Prototype Generation and Matching to resolve Few-Shot Segmentation (FSS), which aims to segment target regions in unlabeled query images based on lab…

Activating Self-Attention for Multi-Scene Absolute Pose Regression

Miso Lee, Jihwan Kim, Jae-Pil Heo

Multi-scene absolute pose regression addresses the demand for fast and memory-efficient camera pose estimation across various real-world environments. Nowadays, transformer-based m…

Long-term Pre-training for Temporal Action Detection with Transformers

Jihwan Kim, Miso Lee, Jae-Pil Heo

Temporal action detection (TAD) is challenging, yet fundamental for real-world video applications. Recently, DETR-based models for TAD have been prevailing thanks to their unique b…

Boundary-Recovering Network for Temporal Action Detection

Jihwan Kim, Jaehyun Choi, Yerim Jeon +1

Temporal action detection (TAD) is challenging, yet fundamental for real-world video applications. Large temporal scale variation of actions is one of the most primary difficulties…

Prediction-Feedback DETR for Temporal Action Detection

Jihwan Kim, Miso Lee, Cheol-Ho Cho +2

Temporal Action Detection (TAD) is fundamental yet challenging for real-world video applications. Leveraging the unique benefits of transformers, various DETR-based approaches have…

Mutually-Aware Feature Learning for Few-Shot Object Counting

Yerim Jeon, Subeen Lee, Jihwan Kim +1

Few-shot object counting has garnered significant attention for its practicality as it aims to count target objects in a query image based on given exemplars without additional tra…