Mining more discriminative temporal features to enrich temporal context representation is considered the key to fine-grained action recog-nition.Previous action recognition methods utilize a fixed spatiotemporal windo...Mining more discriminative temporal features to enrich temporal context representation is considered the key to fine-grained action recog-nition.Previous action recognition methods utilize a fixed spatiotemporal window to learn local video representation.However,these methods failed to capture complex motion patterns due to their limited receptive field.To solve the above problems,this paper proposes a lightweight Temporal Pyramid Excitation(TPE)module to capture the short,medium,and long-term temporal context.In this method,Temporal Pyramid(TP)module can effectively expand the temporal receptive field of the network by using the multi-temporal kernel decomposition without significantly increasing the computational cost.In addition,the Multi Excitation module can emphasize temporal importance to enhance the temporal feature representation learning.TPE can be integrated into ResNet50,and building a compact video learning framework-TPENet.Extensive validation experiments on several challenging benchmark(Something-Something V1,Something-Something V2,UCF-101,and HMDB51)datasets demonstrate that our method achieves a preferable balance between computation and accuracy.展开更多
We propose a simple iterative algorithm based on a temporally movable phase modulation process to retrieve the weak temporal phase of laser pulses. This unambiguous method can be used to achieve a high accuracy and to...We propose a simple iterative algorithm based on a temporally movable phase modulation process to retrieve the weak temporal phase of laser pulses. This unambiguous method can be used to achieve a high accuracy and to simultaneously measure the weak temporal phase and temporal profile of pulses, which are almost transform- limited. A detailed analysis shows that this iterative method has valuable potential applications in the charac- terization of pulses with weak temporal phase.展开更多
Time-varying media have recently emerged as a new paradigm for wave manipulation,due to the synergy between the discovery of highly nonlinear materials,such as epsilon-near-zero materials,and the quest for wave applic...Time-varying media have recently emerged as a new paradigm for wave manipulation,due to the synergy between the discovery of highly nonlinear materials,such as epsilon-near-zero materials,and the quest for wave applications,such as magnet-free nonreciprocity,multimode light shaping,and ultrafast switching.In this review,we provide a comprehensive discussion of the recent progress achieved with photonic metamaterials whose properties stem from their modulation in time.We review the basic concepts underpinning temporal switching and its relation with spatial scattering and deploy the resulting insight to review photonic time-crystals and their emergent research avenues,such as topological and non-Hermitian physics.We then extend our discussion to account for spatiotemporal modulation and its applications to nonreciprocity,synthetic motion,giant anisotropy,amplification,and many other effects.Finally,we conclude with a review of the most attractive experimental avenues recently demonstrated and provide a few perspectives on emerging trends for future implementations of time-modulation in photonics.展开更多
基金supported by the research team of Xi’an Traffic Engineering Institute and the Young and middle-aged fund project of Xi’an Traffic Engineering Institute (2022KY-02).
文摘Mining more discriminative temporal features to enrich temporal context representation is considered the key to fine-grained action recog-nition.Previous action recognition methods utilize a fixed spatiotemporal window to learn local video representation.However,these methods failed to capture complex motion patterns due to their limited receptive field.To solve the above problems,this paper proposes a lightweight Temporal Pyramid Excitation(TPE)module to capture the short,medium,and long-term temporal context.In this method,Temporal Pyramid(TP)module can effectively expand the temporal receptive field of the network by using the multi-temporal kernel decomposition without significantly increasing the computational cost.In addition,the Multi Excitation module can emphasize temporal importance to enhance the temporal feature representation learning.TPE can be integrated into ResNet50,and building a compact video learning framework-TPENet.Extensive validation experiments on several challenging benchmark(Something-Something V1,Something-Something V2,UCF-101,and HMDB51)datasets demonstrate that our method achieves a preferable balance between computation and accuracy.
基金Supported by the National Natural Science Foundation of China under Grant No 61205103
文摘We propose a simple iterative algorithm based on a temporally movable phase modulation process to retrieve the weak temporal phase of laser pulses. This unambiguous method can be used to achieve a high accuracy and to simultaneously measure the weak temporal phase and temporal profile of pulses, which are almost transform- limited. A detailed analysis shows that this iterative method has valuable potential applications in the charac- terization of pulses with weak temporal phase.
基金funding from the Engineering and Physical Sciences Research Council via an EPSRC Doctoral Prize Fellowship (Grant No. EP/T51780X/1)a Junior Fellowship of the Simons Society of Fellows (855344,EG)+5 种基金funding from Fundação para a Ciência e a Tecnologia and Instituto de Telecomunicações under project UIDB/50008/2020funded by the CEEC Individual program from Fundação para a Ciência e a Tecnologia with reference CEECIND/02947/2020funding from the Engineering and Physical Sciences Research Council (EP/V048880)funding from the Gordon and Betty More Foundationfunding from the Department of Defense, the Simons Foundationthe Air Force Office of Scientific Research MURI program
文摘Time-varying media have recently emerged as a new paradigm for wave manipulation,due to the synergy between the discovery of highly nonlinear materials,such as epsilon-near-zero materials,and the quest for wave applications,such as magnet-free nonreciprocity,multimode light shaping,and ultrafast switching.In this review,we provide a comprehensive discussion of the recent progress achieved with photonic metamaterials whose properties stem from their modulation in time.We review the basic concepts underpinning temporal switching and its relation with spatial scattering and deploy the resulting insight to review photonic time-crystals and their emergent research avenues,such as topological and non-Hermitian physics.We then extend our discussion to account for spatiotemporal modulation and its applications to nonreciprocity,synthetic motion,giant anisotropy,amplification,and many other effects.Finally,we conclude with a review of the most attractive experimental avenues recently demonstrated and provide a few perspectives on emerging trends for future implementations of time-modulation in photonics.
