Search

In the context of paid research studies and clinical trials, budget considerations and patient sampling from available populations are subject to inherent constraints. We introduce the R package CDsampling, which is the first to our knowledge to integrate optimal design theories within the framework of constrained sampling. This package offers the possibility to find both D-optimal approximate and exact allocations for samplings with or without constraints. Additionally, it provides functions to find constrained uniform sampling as a robust sampling strategy when the model information is limited. To demonstrate its efficacy, we provide simulated examples and a real-data example with datasets embedded in the package and compare them with classical sampling methods. Furthermore, it revisits the theoretical results of the Fisher information matrix for generalized linear models (including regular linear regression model) and multinomial logistic models, offering functions for its computation.

SMORE (Chen et al., 2023) recently proposed the concept of semantic regular expressions that extend the classical formalism with a primitive to query external oracles such as databases and large language models (LLMs). Such patterns can be used to identify lines of text containing references to semantic concepts such as cities, celebrities, political entities, etc. The focus in their paper was on automatically synthesizing semantic regular expressions from positive and negative examples. In this paper, we study the membership testing problem: First, We present a two-pass NFA-based algorithm to determine whether a string $w$ matches a semantic regular expression (SemRE) $r$ in $O(|r|^2 |w|^2 + |r| |w|^3)$ time, assuming the oracle responds to each query in unit time. In common situations, where oracle queries are not nested, we show that this procedure runs in $O(|r|^2 |w|^2)$ time. Experiments with a prototype implementation of this algorithm validate our theoretical analysis, and show that the procedure massively outperforms a dynamic programming-based baseline, and incurs a $\approx 2 \times$ overhead over the time needed for interaction with the oracle. Next, We establish connections between SemRE membership testing and the triangle finding problem from graph theory, which suggest that developing algorithms which are simultaneously practical and asymptotically faster might be challenging. Furthermore, algorithms for classical regular expressions primarily aim to optimize their time and memory consumption. In contrast, an important consideration in our setting is to minimize the cost of invoking the oracle. We demonstrate an $\Omega(|w|^2)$ lower bound on the number of oracle queries necessary to make this determination.

Recent advances in diffusion-based robot policies have demonstrated significant potential in imitating multi-modal behaviors. However, these approaches typically require large quantities of demonstration data paired with corresponding robot action labels, creating a substantial data collection burden. In this work, we propose a plan-then-control framework aimed at improving the action-data efficiency of inverse dynamics controllers by leveraging observational demonstration data. Specifically, we adopt a Deep Koopman Operator framework to model the dynamical system and utilize observation-only trajectories to learn a latent action representation. This latent representation can then be effectively mapped to real high-dimensional continuous actions using a linear action decoder, requiring minimal action-labeled data. Through experiments on simulated robot manipulation tasks and a real robot experiment with multi-modal expert demonstrations, we demonstrate that our approach significantly enhances action-data efficiency and achieves high task success rates with limited action data.

We present a contrastive learning framework based on in-the-wild hand images tailored for pre-training 3D hand pose estimators, dubbed HandCLR. Pre-training on large-scale images achieves promising results in various tasks, but prior 3D hand pose pre-training methods have not fully utilized the potential of diverse hand images accessible from in-the-wild videos. To facilitate scalable pre-training, we first prepare an extensive pool of hand images from in-the-wild videos and design our method with contrastive learning. Specifically, we collected over 2.0M hand images from recent human-centric videos, such as 100DOH and Ego4D. To extract discriminative information from these images, we focus on the similarity of hands; pairs of similar hand poses originating from different samples, and propose a novel contrastive learning method that embeds similar hand pairs closer in the latent space. Our experiments demonstrate that our method outperforms conventional contrastive learning approaches that produce positive pairs sorely from a single image with data augmentation. We achieve significant improvements over the state-of-the-art method in various datasets, with gains of 15% on FreiHand, 10% on DexYCB, and 4% on AssemblyHands., Comment: HANDS@ECCV24 (Extended Abstracts)

Delving into the realm of egocentric vision, the advancement of referring video object segmentation (RVOS) stands as pivotal in understanding human activities. However, existing RVOS task primarily relies on static attributes such as object names to segment target objects, posing challenges in distinguishing target objects from background objects and in identifying objects undergoing state changes. To address these problems, this work proposes a novel action-aware RVOS setting called ActionVOS, aiming at segmenting only active objects in egocentric videos using human actions as a key language prompt. This is because human actions precisely describe the behavior of humans, thereby helping to identify the objects truly involved in the interaction and to understand possible state changes. We also build a method tailored to work under this specific setting. Specifically, we develop an action-aware labeling module with an efficient action-guided focal loss. Such designs enable ActionVOS model to prioritize active objects with existing readily-available annotations. Experimental results on VISOR dataset reveal that ActionVOS significantly reduces the mis-segmentation of inactive objects, confirming that actions help the ActionVOS model understand objects' involvement. Further evaluations on VOST and VSCOS datasets show that the novel ActionVOS setting enhances segmentation performance when encountering challenging circumstances involving object state changes. We will make our implementation available at https://github.com/ut-vision/ActionVOS., Comment: This paper is accepted by ECCV2024. Code will be released at https://github.com/ut-vision/ActionVOS

Compared with visual signals, Inertial Measurement Units (IMUs) placed on human limbs can capture accurate motion signals while being robust to lighting variation and occlusion. While these characteristics are intuitively valuable to help egocentric action recognition, the potential of IMUs remains under-explored. In this work, we present a novel method for action recognition that integrates motion data from body-worn IMUs with egocentric video. Due to the scarcity of labeled multimodal data, we design an MAE-based self-supervised pretraining method, obtaining strong multi-modal representations via modeling the natural correlation between visual and motion signals. To model the complex relation of multiple IMU devices placed across the body, we exploit the collaborative dynamics in multiple IMU devices and propose to embed the relative motion features of human joints into a graph structure. Experiments show our method can achieve state-of-the-art performance on multiple public datasets. The effectiveness of our MAE-based pretraining and graph-based IMU modeling are further validated by experiments in more challenging scenarios, including partially missing IMU devices and video quality corruption, promoting more flexible usages in the real world., Comment: ECCV 2024

In this report, we present our solutions to the EgoVis Challenges in CVPR 2024, including five tracks in the Ego4D challenge and three tracks in the EPIC-Kitchens challenge. Building upon the video-language two-tower model and leveraging our meticulously organized egocentric video data, we introduce a novel foundation model called EgoVideo. This model is specifically designed to cater to the unique characteristics of egocentric videos and provides strong support for our competition submissions. In the Ego4D challenges, we tackle various tasks including Natural Language Queries, Step Grounding, Moment Queries, Short-term Object Interaction Anticipation, and Long-term Action Anticipation. In addition, we also participate in the EPIC-Kitchens challenge, where we engage in the Action Recognition, Multiple Instance Retrieval, and Domain Adaptation for Action Recognition tracks. By adapting EgoVideo to these diverse tasks, we showcase its versatility and effectiveness in different egocentric video analysis scenarios, demonstrating the powerful representation ability of EgoVideo as an egocentric foundation model. Our codebase and pretrained models are publicly available at https://github.com/OpenGVLab/EgoVideo., Comment: Champion solutions in the EgoVis CVPR 2024 workshop

The accuracy of phaseless auxiliary-field quantum Monte Carlo (ph-AFQMC) can be systematically improved with better trial states. Using multi-Slater determinant trial states, ph-AFQMC has the potential to faithfully treat strongly correlated systems, while balancing the static and dynamical correlations on an equal footing. This preprint presents an implementation and application of graphics processing unit-accelerated ph-AFQMC, for multi-Slater determinant trial wavefunctions (GPU-accelerated MSD-AFQMC), to enable efficient simulation of large-scale, strongly correlated systems. This approach allows for nearly-exact computation of ground state energies in multi-reference systems. Our GPU-accelerated MSD-AFQMC is implemented in the open-source code \texttt{ipie}, a Python-based AFQMC package [\textit{J. Chem. Theory Comput.}, 2022, 19(1): 109-121]. We benchmark the performance of the GPU code on transition-metal clusters like [Cu$_2$O$_2$]$^{2+}$ and [Fe$_2$S$_2$(SCH$_3$)]$^{2-}$. The GPU code achieves at least sixfold speedup in both cases, comparing the timings of a single A100 GPU to that of a 32-CPU node. For [Fe$_2$S$_2$(SCH$_3$)]$^{2-}$, we demonstrate that our GPU MSD-AFQMC can recover the dynamical correlation necessary for chemical accuracy with an MSD trial, despite the large number of determinants required ($>10^5$). Our work significantly enhances the efficiency of MSD-AFQMC calculations for large, strongly correlated molecules by utilizing GPUs, offering a promising path for exploring the electronic structure of transition metal complexes., Comment: 6 pages, 2 figures

Recent advancements in Text-to-image (T2I) generation have witnessed a shift from adapting text to fixed backgrounds to creating images around text. Traditional approaches are often limited to generate layouts within static images for effective text placement. Our proposed approach, TextCenGen, introduces a dynamic adaptation of the blank region for text-friendly image generation, emphasizing text-centric design and visual harmony generation. Our method employs force-directed attention guidance in T2I models to generate images that strategically reserve whitespace for pre-defined text areas, even for text or icons at the golden ratio. Observing how cross-attention maps affect object placement, we detect and repel conflicting objects using a force-directed graph approach, combined with a Spatial Excluding Cross-Attention Constraint for smooth attention in whitespace areas. As a novel task in graphic design, experiments indicate that TextCenGen outperforms existing methods with more harmonious compositions. Furthermore, our method significantly enhances T2I model outcomes on our specially collected prompt datasets, catering to varied text positions. These results demonstrate the efficacy of TextCenGen in creating more harmonious and integrated text-image compositions., Comment: 7 pages, 7 figures

Being able to map the activities of others into one's own point of view is one fundamental human skill even from a very early age. Taking a step toward understanding this human ability, we introduce EgoExoLearn, a large-scale dataset that emulates the human demonstration following process, in which individuals record egocentric videos as they execute tasks guided by demonstration videos. Focusing on the potential applications in daily assistance and professional support, EgoExoLearn contains egocentric and demonstration video data spanning 120 hours captured in daily life scenarios and specialized laboratories. Along with the videos we record high-quality gaze data and provide detailed multimodal annotations, formulating a playground for modeling the human ability to bridge asynchronous procedural actions from different viewpoints. To this end, we present benchmarks such as cross-view association, cross-view action planning, and cross-view referenced skill assessment, along with detailed analysis. We expect EgoExoLearn can serve as an important resource for bridging the actions across views, thus paving the way for creating AI agents capable of seamlessly learning by observing humans in the real world. Code and data can be found at: https://github.com/OpenGVLab/EgoExoLearn, Comment: CVPR 2024

We introduce InternVideo2, a new family of video foundation models (ViFM) that achieve the state-of-the-art results in video recognition, video-text tasks, and video-centric dialogue. Our core design is a progressive training approach that unifies the masked video modeling, crossmodal contrastive learning, and next token prediction, scaling up the video encoder size to 6B parameters. At the data level, we prioritize spatiotemporal consistency by semantically segmenting videos and generating video-audio-speech captions. This improves the alignment between video and text. Through extensive experiments, we validate our designs and demonstrate superior performance on over 60 video and audio tasks. Notably, our model outperforms others on various video-related dialogue and long video understanding benchmarks, highlighting its ability to reason and comprehend longer contexts. Code and models are available at https://github.com/OpenGVLab/InternVideo/tree/main/InternVideo2/., Comment: a technical report about video understanding (accepted to ECCV2024)

Understanding videos is one of the fundamental directions in computer vision research, with extensive efforts dedicated to exploring various architectures such as RNN, 3D CNN, and Transformers. The newly proposed architecture of state space model, e.g., Mamba, shows promising traits to extend its success in long sequence modeling to video modeling. To assess whether Mamba can be a viable alternative to Transformers in the video understanding domain, in this work, we conduct a comprehensive set of studies, probing different roles Mamba can play in modeling videos, while investigating diverse tasks where Mamba could exhibit superiority. We categorize Mamba into four roles for modeling videos, deriving a Video Mamba Suite composed of 14 models/modules, and evaluating them on 12 video understanding tasks. Our extensive experiments reveal the strong potential of Mamba on both video-only and video-language tasks while showing promising efficiency-performance trade-offs. We hope this work could provide valuable data points and insights for future research on video understanding. Code is public: https://github.com/OpenGVLab/video-mamba-suite., Comment: Technical Report

In the development of science, accurate and reproducible documentation of the experimental process is crucial. Automatic recognition of the actions in experiments from videos would help experimenters by complementing the recording of experiments. Towards this goal, we propose FineBio, a new fine-grained video dataset of people performing biological experiments. The dataset consists of multi-view videos of 32 participants performing mock biological experiments with a total duration of 14.5 hours. One experiment forms a hierarchical structure, where a protocol consists of several steps, each further decomposed into a set of atomic operations. The uniqueness of biological experiments is that while they require strict adherence to steps described in each protocol, there is freedom in the order of atomic operations. We provide hierarchical annotation on protocols, steps, atomic operations, object locations, and their manipulation states, providing new challenges for structured activity understanding and hand-object interaction recognition. To find out challenges on activity understanding in biological experiments, we introduce baseline models and results on four different tasks, including (i) step segmentation, (ii) atomic operation detection (iii) object detection, and (iv) manipulated/affected object detection. Dataset and code are available from https://github.com/aistairc/FineBio.

Understanding human actions from videos of first-person view poses significant challenges. Most prior approaches explore representation learning on egocentric videos only, while overlooking the potential benefit of exploiting existing large-scale third-person videos. In this paper, (1) we develop EgoInstructor, a retrieval-augmented multimodal captioning model that automatically retrieves semantically relevant third-person instructional videos to enhance the video captioning of egocentric videos. (2) For training the cross-view retrieval module, we devise an automatic pipeline to discover ego-exo video pairs from distinct large-scale egocentric and exocentric datasets. (3) We train the cross-view retrieval module with a novel EgoExoNCE loss that pulls egocentric and exocentric video features closer by aligning them to shared text features that describe similar actions. (4) Through extensive experiments, our cross-view retrieval module demonstrates superior performance across seven benchmarks. Regarding egocentric video captioning, EgoInstructor exhibits significant improvements by leveraging third-person videos as references. Project page is available at: https://jazzcharles.github.io/Egoinstructor/, Comment: CVPR 2024. Project page is available at: https://jazzcharles.github.io/Egoinstructor/

While several long-form VideoQA datasets have been introduced, the length of both videos used to curate questions and sub-clips of clues leveraged to answer those questions have not yet reached the criteria for genuine long-form video understanding. Moreover, their QAs are unduly narrow and modality-biased, lacking a wider view of understanding long-term video content with rich dynamics and complex narratives. To remedy this, we introduce MoVQA, a long-form movie question-answering dataset, and benchmark to assess the diverse cognitive capabilities of multimodal systems rely on multi-level temporal lengths, with considering both video length and clue length. Additionally, to take a step towards human-level understanding in long-form video, versatile and multimodal question-answering is designed from the moviegoer-perspective to assess the model capabilities on various perceptual and cognitive axes.Through analysis involving various baselines reveals a consistent trend: the performance of all methods significantly deteriorate with increasing video and clue length. Meanwhile, our established baseline method has shown some improvements, but there is still ample scope for enhancement on our challenging MoVQA dataset. We expect our MoVQA to provide a new perspective and encourage inspiring works on long-form video understanding research.

We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). 740 participants from 13 cities worldwide performed these activities in 123 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,286 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions -- including a novel "expert commentary" done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources are open sourced to fuel new research in the community. Project page: http://ego-exo4d-data.org/, Comment: Expanded manuscript (compared to arxiv v1 from Nov 2023 and CVPR 2024 paper from June 2024) for more comprehensive dataset and benchmark presentation, plus new results on v2 data release

Unconventional superconductivity in bulk materials under ambient pressure is extremely rare among the 3d transition metal compounds outside the layered cuprates and iron-based family. It is predominantly linked to highly anisotropic electronic properties and quasi-two-dimensional (2D) Fermi surfaces. To date, the only known example of a Co-based exotic superconductor is the hydrated layered cobaltate, Na$_{x}$CoO$_{2}\cdot$ yH$_{2}$O, and its superconductivity is realized in the vicinity of a spin-1/2 Mott state. However, the nature of the superconductivity in these materials is still a subject of intense debate, and therefore, finding a new class of superconductors will help unravel the mysteries of their unconventional superconductivity. Here we report the discovery of superconductivity at $\sim$ 6.3 K in our newly synthesized layered compound Na$_{2}$CoSe$_{2}$O, in which the edge-shared CoSe$_{6}$ octahedra form [CoSe$_{2}$] layers with a perfect triangular lattice of Co ions. It is the first 3d transition metal oxychalcogenide superconductor with distinct structural and chemical characteristics. Despite its relatively low $T_{c}$, this material exhibits very high superconducting upper critical fields, $\mu_{0}H_{c2}(0)$, which far exceeds the Pauli paramagnetic limit by a factor of 3 - 4. First-principles calculations show that Na$_{2}$CoSe$_{2}$O is a rare example of a negative charge transfer superconductor. This cobalt oxychalcogenide with a geometrical frustration among Co spins shows great potential as a highly appealing candidate for the realization of unconventional and/or high-$T_{c}$ superconductivity beyond the well-established Cu- and Fe-based superconductor families and opens a new field in the physics and chemistry of low-dimensional superconductors.

In many real-world scenarios (e.g., academic networks, social platforms), different types of entities are not only associated with texts but also connected by various relationships, which can be abstracted as Text-Attributed Heterogeneous Graphs (TAHGs). Current pretraining tasks for Language Models (LMs) primarily focus on separately learning the textual information of each entity and overlook the crucial aspect of capturing topological connections among entities in TAHGs. In this paper, we present a new pretraining framework for LMs that explicitly considers the topological and heterogeneous information in TAHGs. Firstly, we define a context graph as neighborhoods of a target node within specific orders and propose a topology-aware pretraining task to predict nodes involved in the context graph by jointly optimizing an LM and an auxiliary heterogeneous graph neural network. Secondly, based on the observation that some nodes are text-rich while others have little text, we devise a text augmentation strategy to enrich textless nodes with their neighbors' texts for handling the imbalance issue. We conduct link prediction and node classification tasks on three datasets from various domains. Experimental results demonstrate the superiority of our approach over existing methods and the rationality of each design. Our code is available at https://github.com/Hope-Rita/THLM., Comment: Accepted by EMNLP 2023 Findings

Point-level supervised temporal action localization (PTAL) aims at recognizing and localizing actions in untrimmed videos where only a single point (frame) within every action instance is annotated in training data. Without temporal annotations, most previous works adopt the multiple instance learning (MIL) framework, where the input video is segmented into non-overlapped short snippets, and action classification is performed independently on every short snippet. We argue that the MIL framework is suboptimal for PTAL because it operates on separated short snippets that contain limited temporal information. Therefore, the classifier only focuses on several easy-to-distinguish snippets instead of discovering the whole action instance without missing any relevant snippets. To alleviate this problem, we propose a novel method that localizes actions by generating and evaluating action proposals of flexible duration that involve more comprehensive temporal information. Moreover, we introduce an efficient clustering algorithm to efficiently generate dense pseudo labels that provide stronger supervision, and a fine-grained contrastive loss to further refine the quality of pseudo labels. Experiments show that our proposed method achieves competitive or superior performance to the state-of-the-art methods and some fully-supervised methods on four benchmarks: ActivityNet 1.3, THUMOS 14, GTEA, and BEOID datasets., Comment: BMVC 2023

In this paper, we address the problem of designing an experimental plan with both discrete and continuous factors under fairly general parametric statistical models. We propose a new algorithm, named ForLion, to search for locally optimal approximate designs under the D-criterion. The algorithm performs an exhaustive search in a design space with mixed factors while keeping high efficiency and reducing the number of distinct experimental settings. Its optimality is guaranteed by the general equivalence theorem. We present the relevant theoretical results for multinomial logit models (MLM) and generalized linear models (GLM), and demonstrate the superiority of our algorithm over state-of-the-art design algorithms using real-life experiments under MLM and GLM. Our simulation studies show that the ForLion algorithm could reduce the number of experimental settings by 25% or improve the relative efficiency of the designs by 17.5% on average. Our algorithm can help the experimenters reduce the time cost, the usage of experimental devices, and thus the total cost of their experiments while preserving high efficiencies of the designs., Comment: 36 pages, 7 tables, 5 figures

Most existing forecasting systems are memory-based methods, which attempt to mimic human forecasting ability by employing various memory mechanisms and have progressed in temporal modeling for memory dependency. Nevertheless, an obvious weakness of this paradigm is that it can only model limited historical dependence and can not transcend the past. In this paper, we rethink the temporal dependence of event evolution and propose a novel memory-anticipation-based paradigm to model an entire temporal structure, including the past, present, and future. Based on this idea, we present Memory-and-Anticipation Transformer (MAT), a memory-anticipation-based approach, to address the online action detection and anticipation tasks. In addition, owing to the inherent superiority of MAT, it can process online action detection and anticipation tasks in a unified manner. The proposed MAT model is tested on four challenging benchmarks TVSeries, THUMOS'14, HDD, and EPIC-Kitchens-100, for online action detection and anticipation tasks, and it significantly outperforms all existing methods. Code is available at https://github.com/Echo0125/Memory-and-Anticipation-Transformer., Comment: ICCV 2023 Camera Ready

With the exponential growth of video data, there is an urgent need for automated technology to analyze and comprehend video content. However, existing video understanding models are often task-specific and lack a comprehensive capability of handling diverse tasks. The success of large language models (LLMs) like GPT has demonstrated their impressive abilities in sequence causal reasoning. Building upon this insight, we propose a novel framework called VideoLLM that leverages the sequence reasoning capabilities of pre-trained LLMs from natural language processing (NLP) for video sequence understanding. VideoLLM incorporates a carefully designed Modality Encoder and Semantic Translator, which convert inputs from various modalities into a unified token sequence. This token sequence is then fed into a decoder-only LLM. Subsequently, with the aid of a simple task head, our VideoLLM yields an effective unified framework for different kinds of video understanding tasks. To evaluate the efficacy of VideoLLM, we conduct extensive experiments using multiple LLMs and fine-tuning methods. We evaluate our VideoLLM on eight tasks sourced from four different datasets. The experimental results demonstrate that the understanding and reasoning capabilities of LLMs can be effectively transferred to video understanding tasks. We release the code at https://github.com/cg1177/VideoLLM., Comment: Technical Report

The Multiplane Image (MPI), containing a set of fronto-parallel RGBA layers, is an effective and efficient representation for view synthesis from sparse inputs. Yet, its fixed structure limits the performance, especially for surfaces imaged at oblique angles. We introduce the Structural MPI (S-MPI), where the plane structure approximates 3D scenes concisely. Conveying RGBA contexts with geometrically-faithful structures, the S-MPI directly bridges view synthesis and 3D reconstruction. It can not only overcome the critical limitations of MPI, i.e., discretization artifacts from sloped surfaces and abuse of redundant layers, and can also acquire planar 3D reconstruction. Despite the intuition and demand of applying S-MPI, great challenges are introduced, e.g., high-fidelity approximation for both RGBA layers and plane poses, multi-view consistency, non-planar regions modeling, and efficient rendering with intersected planes. Accordingly, we propose a transformer-based network based on a segmentation model. It predicts compact and expressive S-MPI layers with their corresponding masks, poses, and RGBA contexts. Non-planar regions are inclusively handled as a special case in our unified framework. Multi-view consistency is ensured by sharing global proxy embeddings, which encode plane-level features covering the complete 3D scenes with aligned coordinates. Intensive experiments show that our method outperforms both previous state-of-the-art MPI-based view synthesis methods and planar reconstruction methods., Comment: Accepted to CVPR2023

Object affordance is an important concept in hand-object interaction, providing information on action possibilities based on human motor capacity and objects' physical property thus benefiting tasks such as action anticipation and robot imitation learning. However, the definition of affordance in existing datasets often: 1) mix up affordance with object functionality; 2) confuse affordance with goal-related action; and 3) ignore human motor capacity. This paper proposes an efficient annotation scheme to address these issues by combining goal-irrelevant motor actions and grasp types as affordance labels and introducing the concept of mechanical action to represent the action possibilities between two objects. We provide new annotations by applying this scheme to the EPIC-KITCHENS dataset and test our annotation with tasks such as affordance recognition, hand-object interaction hotspots prediction, and cross-domain evaluation of affordance. The results show that models trained with our annotation can distinguish affordance from other concepts, predict fine-grained interaction possibilities on objects, and generalize through different domains., Comment: WACV 2023. Refined version of Workshop article arXiv:2206.05424

In this report, we present our champion solutions to five tracks at Ego4D challenge. We leverage our developed InternVideo, a video foundation model, for five Ego4D tasks, including Moment Queries, Natural Language Queries, Future Hand Prediction, State Change Object Detection, and Short-term Object Interaction Anticipation. InternVideo-Ego4D is an effective paradigm to adapt the strong foundation model to the downstream ego-centric video understanding tasks with simple head designs. In these five tasks, the performance of InternVideo-Ego4D comprehensively surpasses the baseline methods and the champions of CVPR2022, demonstrating the powerful representation ability of InternVideo as a video foundation model. Our code will be released at https://github.com/OpenGVLab/ego4d-eccv2022-solutions, Comment: Technical report in 2nd International Ego4D Workshop@ECCV 2022. Code will be released at https://github.com/OpenGVLab/ego4d-eccv2022-solutions

Few-shot action recognition aims to recognize novel action classes using only a small number of labeled training samples. In this work, we propose a novel approach that first summarizes each video into compound prototypes consisting of a group of global prototypes and a group of focused prototypes, and then compares video similarity based on the prototypes. Each global prototype is encouraged to summarize a specific aspect from the entire video, for example, the start/evolution of the action. Since no clear annotation is provided for the global prototypes, we use a group of focused prototypes to focus on certain timestamps in the video. We compare video similarity by matching the compound prototypes between the support and query videos. The global prototypes are directly matched to compare videos from the same perspective, for example, to compare whether two actions start similarly. For the focused prototypes, since actions have various temporal variations in the videos, we apply bipartite matching to allow the comparison of actions with different temporal positions and shifts. Experiments demonstrate that our proposed method achieves state-of-the-art results on multiple benchmarks., Comment: ECCV 2022

We consider constrained sampling problems in paid research studies or clinical trials. When qualified volunteers are more than the budget allowed, we recommend a D-optimal sampling strategy based on the optimal design theory and develop a constrained lift-one algorithm to find the optimal allocation. Unlike the literature which mainly deals with linear models, our solution solves the constrained sampling problem under fairly general statistical models, including generalized linear models and multinomial logistic models, and with more general constraints. We justify theoretically the optimality of our sampling strategy and show by simulation studies and real-world examples the advantages over simple random sampling and proportionally stratified sampling strategies., Comment: 30 pages

Quantum computing and quantum Monte Carlo (QMC) are respectively the state-of-the-art quantum and classical computing methods for understanding many-body quantum systems. Here, we propose a hybrid quantum-classical algorithm that integrates these two methods, inheriting their distinct features in efficient representation and manipulation of quantum states and overcoming their limitations. We first introduce non-stoquasticity indicators (NSIs) and their upper bounds, which measure the sign problem, the most notable limitation of QMC. We show that our algorithm could greatly mitigate the sign problem, which decreases NSIs with the assistance of quantum computing. Meanwhile, the use of quantum Monte Carlo also increases the expressivity of shallow quantum circuits, allowing more accurate computation that is conventionally achievable only with much deeper circuits. We numerically test and verify the method for the N$_2$ molecule (12 qubits) and the Hubbard model (16 qubits). Our work paves the way to solving practical problems with intermediate-scale and early-fault tolerant quantum computers, with potential applications in chemistry, condensed matter physics, materials, high energy physics, etc.

Object affordance is an important concept in human-object interaction, providing information on action possibilities based on human motor capacity and objects' physical property thus benefiting tasks such as action anticipation and robot imitation learning. However, existing datasets often: 1) mix up affordance with object functionality; 2) confuse affordance with goal-related action; and 3) ignore human motor capacity. This paper proposes an efficient annotation scheme to address these issues by combining goal-irrelevant motor actions and grasp types as affordance labels and introducing the concept of mechanical action to represent the action possibilities between two objects. We provide new annotations by applying this scheme to the EPIC-KITCHENS dataset and test our annotation with tasks such as affordance recognition. We qualitatively verify that models trained with our annotation can distinguish affordance and mechanical actions., Comment: Technical report for CVPR 2022 EPIC-Ego4D Workshop

Quantum imaginary time evolution (QITE) is one of the promising candidates for finding eigenvalues and eigenstates of a Hamiltonian. However, the original QITE proposal [Nat. Phys. 16, 205-210 (2020)], which approximates the imaginary time evolution by real time evolution, suffers from large circuit depth and measurements due to the size of the Pauli operator pool and Trotterization. To alleviate the requirement for deep circuits, we propose a time-dependent drifting scheme inspired by the qDRIFT algorithm [Phys. Rev. Lett 123, 070503 (2019)], which randomly draws a Pauli term out of the approximated unitary operation generators of QITE according to the strength and rescales that term by the total strength of the Pauli terms. We show that this drifting scheme removes the depth dependency on size of the operator pool and converges inverse linearly to the number of steps. We further propose a deterministic algorithm that selects the dominant Pauli term to reduce the fluctuation for the ground state preparation. Meanwhile, we introduce an efficient measurement reduction scheme across Trotter steps, which removes its cost dependence on the number of iterations, and a measurement distribution protocol for different observables within each time step. We also analyze the main source of error for our scheme both theoretically and numerically. We numerically test the validity of depth reduction, convergence performance, and faithfulness of measurement reduction approximation of our algorithms on LiH, BeH$_2$ and N$_2$ molecules. In particular, the results on LiH molecule give circuit depths comparable to that of the advanced adaptive variational quantum eigensolver~(VQE) methods while requiring much fewer measurements.

Lane is critical in the vision navigation system of the intelligent vehicle. Naturally, lane is a traffic sign with high-level semantics, whereas it owns the specific local pattern which needs detailed low-level features to localize accurately. Using different feature levels is of great importance for accurate lane detection, but it is still under-explored. In this work, we present Cross Layer Refinement Network (CLRNet) aiming at fully utilizing both high-level and low-level features in lane detection. In particular, it first detects lanes with high-level semantic features then performs refinement based on low-level features. In this way, we can exploit more contextual information to detect lanes while leveraging local detailed lane features to improve localization accuracy. We present ROIGather to gather global context, which further enhances the feature representation of lanes. In addition to our novel network design, we introduce Line IoU loss which regresses the lane line as a whole unit to improve the localization accuracy. Experiments demonstrate that the proposed method greatly outperforms the state-of-the-art lane detection approaches., Comment: CVPR2022 Acceptance

First-person action recognition is a challenging task in video understanding. Because of strong ego-motion and a limited field of view, many backgrounds or noisy frames in a first-person video can distract an action recognition model during its learning process. To encode more discriminative features, the model needs to have the ability to focus on the most relevant part of the video for action recognition. Previous works explored to address this problem by applying temporal attention but failed to consider the global context of the full video, which is critical for determining the relatively significant parts. In this work, we propose a simple yet effective Stacked Temporal Attention Module (STAM) to compute temporal attention based on the global knowledge across clips for emphasizing the most discriminative features. We achieve this by stacking multiple self-attention layers. Instead of naive stacking, which is experimentally proven to be ineffective, we carefully design the input to each self-attention layer so that both the local and global context of the video is considered during generating the temporal attention weights. Experiments demonstrate that our proposed STAM can be built on top of most existing backbones and boost the performance in various datasets., Comment: BMVC 2021

The human gaze is a cost-efficient physiological data that reveals human underlying attentional patterns. The selective attention mechanism helps the cognition system focus on task-relevant visual clues by ignoring the presence of distractors. Thanks to this ability, human beings can efficiently learn from a very limited number of training samples. Inspired by this mechanism, we aim to leverage gaze for medical image analysis tasks with small training data. Our proposed framework includes a backbone encoder and a Selective Attention Network (SAN) that simulates the underlying attention. The SAN implicitly encodes information such as suspicious regions that is relevant to the medical diagnose tasks by estimating the actual human gaze. Then we design a novel Auxiliary Attention Block (AAB) to allow information from SAN to be utilized by the backbone encoder to focus on selective areas. Specifically, this block uses a modified version of a multi-head attention layer to simulate the human visual search procedure. Note that the SAN and AAB can be plugged into different backbones, and the framework can be used for multiple medical image analysis tasks when equipped with task-specific heads. Our method is demonstrated to achieve superior performance on both 3D tumor segmentation and 2D chest X-ray classification tasks. We also show that the estimated gaze probability map of the SAN is consistent with an actual gaze fixation map obtained by board-certified doctors., Comment: BMVC 2021