Yukun Lai

Hao Wen, Jing Huang, Huili Cui et al.

Image-based multi-person reconstruction in wide-field large scenes is critical for crowd analysis and security alert. However, existing methods cannot deal with large scenes containing hundreds of people, which encounter the challenges of large number of people, large variations in human scale, and complex spatial distribution. In this paper, we propose Crowd3D, the first framework to reconstruct the 3D poses, shapes and locations of hundreds of people with global consistency from a single large-scene image. The core of our approach is to convert the problem of complex crowd localization into pixel localization with the help of our newly defined concept, Human-scene Virtual Interaction Point (HVIP). To reconstruct the crowd with global consistency, we propose a progressive reconstruction network based on HVIP by pre-estimating a scene-level camera and a ground plane. To deal with a large number of persons and various human sizes, we also design an adaptive human-centric cropping scheme. Besides, we contribute a benchmark dataset, LargeCrowd, for crowd reconstruction in a large scene. Experimental results demonstrate the effectiveness of the proposed method. The code and datasets will be made public.

Yixiao Li, Xiaoyuan Yang, Weide Liu et al.

As super-resolution (SR) techniques introduce unique distortions that fundamentally differ from those caused by traditional degradation processes (e.g., compression), there is an increasing demand for specialized video quality assessment (VQA) methods tailored to SR-generated content. One critical factor affecting perceived quality is temporal inconsistency, which refers to irregularities between consecutive frames. However, existing VQA approaches rarely quantify this phenomenon or explicitly investigate its relationship with human perception. Moreover, SR videos exhibit amplified inconsistency levels as a result of enhancement processes. In this paper, we propose \textit{Temporal Inconsistency Guidance for Super-resolution Video Quality Assessment (TIG-SVQA)} that underscores the critical role of temporal inconsistency in guiding the quality assessment of SR videos. We first design a perception-oriented approach to quantify frame-wise temporal inconsistency. Based on this, we introduce the Inconsistency Highlighted Spatial Module, which localizes inconsistent regions at both coarse and fine scales. Inspired by the human visual system, we further develop an Inconsistency Guided Temporal Module that performs progressive temporal feature aggregation: (1) a consistency-aware fusion stage in which a visual memory capacity block adaptively determines the information load of each temporal segment based on inconsistency levels, and (2) an informative filtering stage for emphasizing quality-related features. Extensive experiments on both single-frame and multi-frame SR video scenarios demonstrate that our method significantly outperforms state-of-the-art VQA approaches. The code is publicly available at https://github.com/Lighting-YXLI/TIG-SVQA-main.

Mingchen Xu, Jing Wu, Yukun Lai et al.

Techniques for detecting mirrors from static images have witnessed rapid growth in recent years. However, these methods detect mirrors from single input images. Detecting mirrors from video requires further consideration of temporal consistency between frames. We observe that humans can recognize mirror candidates, from just one or two frames, based on their appearance (e.g. shape, color). However, to ensure that the candidate is indeed a mirror (not a picture or a window), we often need to observe more frames for a global view. This observation motivates us to detect mirrors by fusing appearance features extracted from a short-term attention module and context information extracted from a long-term attention module. To evaluate the performance, we build a challenging benchmark dataset of 19,255 frames from 281 videos. Experimental results demonstrate that our method achieves state-of-the-art performance on the benchmark dataset.

Yujing Wang, Yuanbang Liang, Yukun Lai et al.

Detecting whether a model's internal knowledge is sufficient to correctly answer a given question is a fundamental challenge in deploying responsible LLMs. In addition to verbalising the confidence by LLM self-report, more recent methods explore the model internals, such as the hidden states of the response tokens to capture how much knowledge is activated. We argue that such activated knowledge may not align with what the query requires, e.g., capturing the stylistic and length-related features that are uninformative for answering the query. To fill the gap, we propose GRADE (Gradient Dynamics for knowledge gap detection), which quantifies the knowledge gap via the cross-layer rank ratio of the gradient to that of the corresponding hidden state subspace. This is motivated by the property of gradients as estimators of the required knowledge updates for a given target. We validate \modelname{} on six benchmarks, demonstrating its effectiveness and robustness to input perturbations. In addition, we present a case study showing how the gradient chain can generate interpretable explanations of knowledge gaps for long-form answers.

Mingchen Xu, Yukun Lai, Ze Ji et al.

This paper presents MirrorSAM2, the first framework that adapts Segment Anything Model 2 (SAM2) to the task of RGB-D video mirror segmentation. MirrorSAM2 addresses key challenges in mirror detection, such as reflection ambiguity and texture confusion, by introducing four tailored modules: a Depth Warping Module for RGB and depth alignment, a Depth-guided Multi-Scale Point Prompt Generator for automatic prompt generation, a Frequency Detail Attention Fusion Module to enhance structural boundaries, and a Mirror Mask Decoder with a learnable mirror token for refined segmentation. By fully leveraging the complementarity between RGB and depth, MirrorSAM2 extends SAM2's capabilities to the prompt-free setting. To our knowledge, this is the first work to enable SAM2 for automatic video mirror segmentation. Experiments on the VMD and DVMD benchmark demonstrate that MirrorSAM2 achieves SOTA performance, even under challenging conditions such as small mirrors, weak boundaries, and strong reflections.

Gareth Andrews, Sam Endean, Roberto Dyke et al.

Objects that undergo non-rigid deformation are common in the real world. A typical and challenging example is the human faces. While various techniques have been developed for deformable shape registration and classification, benchmarks with detailed labels and landmarks suitable for evaluating such techniques are still limited. In this paper, we present a novel facial dynamic dataset HDFD which addresses the gap of existing datasets, including 4D funny faces with substantial non-isometric deformation, and 4D visual-audio faces of spoken phrases in a minority language (Welsh). Both datasets are captured from 21 participants. The sequences are manually landmarked, with the spoken phrases further rated by a Welsh expert for level of fluency. These are useful for quantitative evaluation of both registration and classification tasks. We further develop a methodology to evaluate several recent non-rigid surface registration techniques, using our dynamic sequences as test cases. The study demonstrates the significance and usefulness of our new dataset --- a challenging benchmark dataset for future techniques.